An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale
arXiv:2010.11929
Abstract
While the Transformer architecture has become the de-facto standard for natural language processing tasks, its applications to computer vision remain limited. In vision, attention is either applied in conjunction with convolutional networks, or used to replace certain components of convolutional networks while keeping their overall structure in place. We show that this reliance on CNNs is not necessary and a pure transformer applied directly to sequences of image patches can perform very well on image classification tasks. When pre-trained on large amounts of data and transferred to multiple mid-sized or small image recognition benchmarks (ImageNet, CIFAR-100, VTAB, etc.), Vision Transformer (ViT) attains excellent results compared to state-of-the-art convolutional networks while requiring substantially fewer computational resources to train.
arXiv commentFine-tuning code and pre-trained models are available at https://github.com/google-research/vision_transformer. ICLR camera-ready version with 2 small modifications: 1) Added a discussion of CLS vs GAP classifier in the appendix, 2) Fixed an error in exaFLOPs computation in Figure 5 and Table 6 (relative performance of models is basically not affected)
References in corpus (12)
- Language Models are Few-Shot Learners
- VisualBERT: A Simple and Performant Baseline for Vision and Language
- Weight Normalization: A Simple Reparameterization to Accelerate Training of Deep Neural Networks
- Generating Long Sequences with Sparse Transformers
- Visual Transformers: Token-based Image Representation and Processing for Computer Vision
- Axial Attention in Multidimensional Transformers
- GShard: Scaling Giant Models with Conditional Computation and Automatic Sharding
- Image Transformer
- A Large-scale Study of Representation Learning with the Visual Task Adaptation Benchmark
- VideoBERT: A Joint Model for Video and Language Representation Learning
- Learning Deep Transformer Models for Machine Translation
- Fixing the train-test resolution discrepancy: FixEfficientNet
Cited by in corpus (1421)
- Learning Transferable Visual Models From Natural Language Supervision
- Transformers in Vision: A Survey
- Learning to Prompt for Vision-Language Models
- Segment Anything in Medical Images
- PVT v2: Improved Baselines with Pyramid Vision Transformer
- Is Space-Time Attention All You Need for Video Understanding?
- DINOv2: Learning Robust Visual Features without Supervision
- BEiT: BERT Pre-Training of Image Transformers
- SegFormer: Simple and Efficient Design for Semantic Segmentation with Transformers
- Medical Image Segmentation Using Deep Learning: A Survey
- TransMorph: Transformer for unsupervised medical image registration
- Segment Anything Model for Medical Image Analysis: an Experimental Study
- ConViT: Improving Vision Transformers with Soft Convolutional Inductive Biases
- CoAtNet: Marrying Convolution and Attention for All Data Sizes
- Seeing biodiversity: perspectives in machine learning for wildlife conservation
- AdaBins: Depth Estimation using Adaptive Bins
- ResViT: Residual vision transformers for multi-modal medical image synthesis
- Human Action Recognition from Various Data Modalities: A Review
- ET-BERT: A Contextualized Datagram Representation with Pre-training Transformers for Encrypted Traffic Classification
- A novel time-frequency Transformer based on self-attention mechanism and its application in fault diagnosis of rolling bearings
- ViLT: Vision-and-Language Transformer Without Convolution or Region Supervision
- Efficiently Modeling Long Sequences with Structured State Spaces
- MedViT: A Robust Vision Transformer for Generalized Medical Image Classification
- Decision Transformer: Reinforcement Learning via Sequence Modeling
- A Review on Deep Learning in UAV Remote Sensing
- A survey of the Vision Transformers and their CNN-Transformer based Variants
- Self-Supervised Representation Learning: Introduction, Advances and Challenges
- A Novel Transformer Based Semantic Segmentation Scheme for Fine-Resolution Remote Sensing Images
- Skeleton-based Action Recognition via Spatial and Temporal Transformer Networks
- Visual Transformers: Token-based Image Representation and Processing for Computer Vision
- TransTrack: Multiple Object Tracking with Transformer
- Very high resolution canopy height maps from RGB imagery using self-supervised vision transformer and convolutional decoder trained on Aerial Lidar
- Deep Learning-enabled Virtual Histological Staining of Biological Samples
- Video-SwinUNet: Spatio-temporal Deep Learning Framework for VFSS Instance Segmentation
- DeepViT: Towards Deeper Vision Transformer
- Florence: A New Foundation Model for Computer Vision
- When Large Language Models Meet Personalization: Perspectives of Challenges and Opportunities
- Sub-Image Anomaly Detection with Deep Pyramid Correspondences
- DA-TransUNet: Integrating Spatial and Channel Dual Attention with Transformer U-Net for Medical Image Segmentation
- Facial Expression Recognition with Visual Transformers and Attentional Selective Fusion
- Waste detection in Pomerania: non-profit project for detecting waste in environment
- DynamicViT: Efficient Vision Transformers with Dynamic Token Sparsification
- Intriguing Properties of Vision Transformers
- Pre-training Enhanced Spatial-temporal Graph Neural Network for Multivariate Time Series Forecasting
- Escaping the Big Data Paradigm with Compact Transformers
- MetaFormer Baselines for Vision
- Intelligent Computing: The Latest Advances, Challenges and Future
- VLMo: Unified Vision-Language Pre-Training with Mixture-of-Modality-Experts
- Towards artificial general intelligence via a multimodal foundation model
- LocalViT: Analyzing Locality in Vision Transformers
- Class-Incremental Learning: A Survey
- Combining EfficientNet and Vision Transformers for Video Deepfake Detection
- Action Transformer: A Self-Attention Model for Short-Time Pose-Based Human Action Recognition
- TransCrowd: weakly-supervised crowd counting with transformers
- Focal Self-attention for Local-Global Interactions in Vision Transformers
- Attention Bottlenecks for Multimodal Fusion
- TransGAN: Two Pure Transformers Can Make One Strong GAN, and That Can Scale Up
- nnFormer: Interleaved Transformer for Volumetric Segmentation
- MonoViT: Self-Supervised Monocular Depth Estimation with a Vision Transformer
- GETNext: Trajectory Flow Map Enhanced Transformer for Next POI Recommendation
- CTformer: Convolution-free Token2Token Dilated Vision Transformer for Low-dose CT Denoising
- Building extraction with vision transformer
- Large AI Models in Health Informatics: Applications, Challenges, and the Future
- Vision Transformers For Weeds and Crops Classification Of High Resolution UAV Images
- A Transformer-Based Feature Segmentation and Region Alignment Method For UAV-View Geo-Localization
- Compute and Energy Consumption Trends in Deep Learning Inference
- DepthFormer: Exploiting Long-Range Correlation and Local Information for Accurate Monocular Depth Estimation
- Hybrid Transformer with Multi-level Fusion for Multimodal Knowledge Graph Completion
- Explainable Artificial Intelligence: A Survey of Needs, Techniques, Applications, and Future Direction
- Efficient Training of Audio Transformers with Patchout
- UNETR: Transformers for 3D Medical Image Segmentation
- SUNet: Swin Transformer UNet for Image Denoising
- Dual Cross-Attention for Medical Image Segmentation
- Collaborative Perception in Autonomous Driving: Methods, Datasets and Challenges
- Rendezvous: Attention Mechanisms for the Recognition of Surgical Action Triplets in Endoscopic Videos
- Revisiting ResNets: Improved Training and Scaling Strategies
- TransVOD: End-to-End Video Object Detection with Spatial-Temporal Transformers
- FILIP: Fine-grained Interactive Language-Image Pre-Training
- WIT: Wikipedia-based Image Text Dataset for Multimodal Multilingual Machine Learning
- You Only Look at One Sequence: Rethinking Transformer in Vision through Object Detection
- H-vmunet: High-order Vision Mamba UNet for Medical Image Segmentation
- A Survey on Deep Learning for Skin Lesion Segmentation
- Light Field Image Super-Resolution with Transformers
- ActionCLIP: A New Paradigm for Video Action Recognition
- Causal Attention for Interpretable and Generalizable Graph Classification
- Pneumonia Detection on chest X-ray images Using Ensemble of Deep Convolutional Neural Networks
- Artificial-intelligence-based molecular classification of diffuse gliomas using rapid, label-free optical imaging
- Learning Language-guided Adaptive Hyper-modality Representation for Multimodal Sentiment Analysis
- FCN-Transformer Feature Fusion for Polyp Segmentation
- Fast Yet Effective Machine Unlearning
- Transformers in Healthcare: A Survey
- MISSFormer: An Effective Medical Image Segmentation Transformer
- Contrastive Masked Autoencoders are Stronger Vision Learners
- Deep Hyperspectral Unmixing using Transformer Network
- Video Transformers: A Survey
- CvT: Introducing Convolutions to Vision Transformers
- Short and Long Range Relation Based Spatio-Temporal Transformer for Micro-Expression Recognition
- The rise of data-driven weather forecasting
- TriTransNet: RGB-D Salient Object Detection with a Triplet Transformer Embedding Network
- Vision Transformer with Attentive Pooling for Robust Facial Expression Recognition
- Improving Chest X-Ray Report Generation by Leveraging Warm Starting
- Image Representations Learned With Unsupervised Pre-Training Contain Human-like Biases
- Unsupervised Point Cloud Representation Learning with Deep Neural Networks: A Survey
- Looking Outside the Window: Wide-Context Transformer for the Semantic Segmentation of High-Resolution Remote Sensing Images
- How Much Can CLIP Benefit Vision-and-Language Tasks?
- CubeMLP: An MLP-based Model for Multimodal Sentiment Analysis and Depression Estimation
- VLT: Vision-Language Transformer and Query Generation for Referring Segmentation
- Multimodal Data Integration for Oncology in the Era of Deep Neural Networks: A Review
- Self-Supervised Learning for Videos: A Survey
- ResT: An Efficient Transformer for Visual Recognition
- Keyword Transformer: A Self-Attention Model for Keyword Spotting
- ViT-V-Net: Vision Transformer for Unsupervised Volumetric Medical Image Registration
- All Tokens Matter: Token Labeling for Training Better Vision Transformers
- DeepSMILE: Contrastive self-supervised pre-training benefits MSI and HRD classification directly from H&E whole-slide images in colorectal and breast cancer
- CaraNet: Context Axial Reverse Attention Network for Segmentation of Small Medical Objects
- Toward Transformer-Based Object Detection
- Self-supervised Pretraining of Visual Features in the Wild
- Deepfake Video Detection Using Convolutional Vision Transformer
- BiTr-Unet: a CNN-Transformer Combined Network for MRI Brain Tumor Segmentation
- SignBERT+: Hand-model-aware Self-supervised Pre-training for Sign Language Understanding
- IL-MCAM: An interactive learning and multi-channel attention mechanism-based weakly supervised colorectal histopathology image classification approach
- An evidential classifier based on Dempster-Shafer theory and deep learning
- A survey on efficient vision transformers: algorithms, techniques, and performance benchmarking
- Do Transformers Really Perform Bad for Graph Representation?
- CLIP2Video: Mastering Video-Text Retrieval via Image CLIP
- Deep Learning for Computational Cytology: A Survey
- HRFormer: High-Resolution Transformer for Dense Prediction
- Learning Representation for Clustering via Prototype Scattering and Positive Sampling
- Supervision Exists Everywhere: A Data Efficient Contrastive Language-Image Pre-training Paradigm
- CenterCLIP: Token Clustering for Efficient Text-Video Retrieval
- Context-Aware Interaction Network for RGB-T Semantic Segmentation
- Shuffle Transformer: Rethinking Spatial Shuffle for Vision Transformer
- SwinFace: A Multi-task Transformer for Face Recognition, Expression Recognition, Age Estimation and Attribute Estimation
- TransBTS: Multimodal Brain Tumor Segmentation Using Transformer
- Salient Object Detection in Optical Remote Sensing Images Driven by Transformer
- Pre-Trained Image Processing Transformer
- Generalized Radiograph Representation Learning via Cross-supervision between Images and Free-text Radiology Reports
- Query2Label: A Simple Transformer Way to Multi-Label Classification
- RaSa: Relation and Sensitivity Aware Representation Learning for Text-based Person Search
- End-to-End Object Detection with Adaptive Clustering Transformer
- DPT: Deformable Patch-based Transformer for Visual Recognition
- Point Cloud Classification Using Content-based Transformer via Clustering in Feature Space
- Chimera: Efficiently Training Large-Scale Neural Networks with Bidirectional Pipelines
- 3DSAM-adapter: Holistic adaptation of SAM from 2D to 3D for promptable tumor segmentation
- TranSMS: Transformers for Super-Resolution Calibration in Magnetic Particle Imaging
- Zero-Shot Out-of-Distribution Detection Based on the Pre-trained Model CLIP
- Self-Supervised Learning with Swin Transformers
- GA2MIF: Graph and Attention Based Two-Stage Multi-Source Information Fusion for Conversational Emotion Detection
- SuperAnimal pretrained pose estimation models for behavioral analysis
- Transformer with Peak Suppression and Knowledge Guidance for Fine-grained Image Recognition
- CDTrans: Cross-domain Transformer for Unsupervised Domain Adaptation
- R2U++: A Multiscale Recurrent Residual U-Net with Dense Skip Connections for Medical Image Segmentation
- Do Vision Transformers See Like Convolutional Neural Networks?
- CPTR: Full Transformer Network for Image Captioning
- ByteTrack: Multi-Object Tracking by Associating Every Detection Box
- CMTR: Cross-modality Transformer for Visible-infrared Person Re-identification
- Diffusion Models, Image Super-Resolution And Everything: A Survey
- ZoomNeXt: A Unified Collaborative Pyramid Network for Camouflaged Object Detection
- Local-Global Context Aware Transformer for Language-Guided Video Segmentation
- Comprehensive evaluation of deep and graph learning on drug-drug interactions prediction
- Sharpness-Aware Minimization for Efficiently Improving Generalization
- TransFuse: Fusing Transformers and CNNs for Medical Image Segmentation
- Sparse R-CNN: End-to-End Object Detection with Learnable Proposals
- Vision-and-Language Navigation: A Survey of Tasks, Methods, and Future Directions
- CSWin Transformer: A General Vision Transformer Backbone with Cross-Shaped Windows
- CLIP-Art: Contrastive Pre-training for Fine-Grained Art Classification
- Image Compressed Sensing Using Non-local Neural Network
- Deep Learning in Automated Power Line Inspection: A Review
- CycleMLP: A MLP-like Architecture for Dense Prediction
- Machine learning with neural networks
- Pretrained Transformers as Universal Computation Engines
- OperA: Attention-Regularized Transformers for Surgical Phase Recognition
- Facilitated machine learning for image-based fruit quality assessment
- Global Self-Attention as a Replacement for Graph Convolution
- TransCAM: Transformer Attention-based CAM Refinement for Weakly Supervised Semantic Segmentation
- A Foundation Language-Image Model of the Retina (FLAIR): Encoding Expert Knowledge in Text Supervision
- LeViT: a Vision Transformer in ConvNet's Clothing for Faster Inference
- Transformer-based Spatial-Temporal Feature Learning for EEG Decoding
- Rethinking Search: Making Domain Experts out of Dilettantes
- Vector-quantized Image Modeling with Improved VQGAN
- VTGAN: Semi-supervised Retinal Image Synthesis and Disease Prediction using Vision Transformers
- Unlocking the Emotional World of Visual Media: An Overview of the Science, Research, and Impact of Understanding Emotion
- SpeechFormer++: A Hierarchical Efficient Framework for Paralinguistic Speech Processing
- An Algorithm-Hardware Co-Optimized Framework for Accelerating N:M Sparse Transformers
- Tracker Meets Night: A Transformer Enhancer for UAV Tracking
- Is attention all you need in medical image analysis? A review
- TransAttUnet: Multi-level Attention-guided U-Net with Transformer for Medical Image Segmentation
- Vision Transformers, a new approach for high-resolution and large-scale mapping of canopy heights
- AS-MLP: An Axial Shifted MLP Architecture for Vision
- Feature Fusion Vision Transformer for Fine-Grained Visual Categorization
- Chasing Sparsity in Vision Transformers: An End-to-End Exploration
- EEGDnet: Fusing Non-Local and Local Self-Similarity for 1-D EEG Signal Denoising with 2-D Transformer
- A Convolutional-Transformer Network for Crack Segmentation with Boundary Awareness
- Contextformer: A Transformer with Spatio-Channel Attention for Context Modeling in Learned Image Compression
- Geometric deep learning reveals the spatiotemporal fingerprint of microscopic motion
- FIgLib & SmokeyNet: Dataset and Deep Learning Model for Real-Time Wildland Fire Smoke Detection
- Part-guided Relational Transformers for Fine-grained Visual Recognition
- Data synthesis and adversarial networks: A review and meta-analysis in cancer imaging
- Combining Recurrent, Convolutional, and Continuous-time Models with Linear State-Space Layers
- Advances and Applications of Computer Vision Techniques in Vehicle Trajectory Generation and Surrogate Traffic Safety Indicators
- CXR-CLIP: Toward Large Scale Chest X-ray Language-Image Pre-training
- HTR-VT: Handwritten Text Recognition with Vision Transformer
- SwinIR: Image Restoration Using Swin Transformer
- Fastformer: Additive Attention Can Be All You Need
- Do You Even Need Attention? A Stack of Feed-Forward Layers Does Surprisingly Well on ImageNet
- MicroSegNet: A Deep Learning Approach for Prostate Segmentation on Micro-Ultrasound Images
- Logic Explained Networks
- CLIP in Medical Imaging: A Survey
- GPT-4 Enhanced Multimodal Grounding for Autonomous Driving: Leveraging Cross-Modal Attention with Large Language Models
- Supervised Compression for Resource-Constrained Edge Computing Systems
- CLIP-VG: Self-paced Curriculum Adapting of CLIP for Visual Grounding
- Multi-Modal Mutual Attention and Iterative Interaction for Referring Image Segmentation
- Temporal Sentence Grounding in Videos: A Survey and Future Directions
- From Static to Dynamic: Adapting Landmark-Aware Image Models for Facial Expression Recognition in Videos
- Mapping global dynamics of benchmark creation and saturation in artificial intelligence
- LDMVFI: Video Frame Interpolation with Latent Diffusion Models
- TrTr: Visual Tracking with Transformer
- Transflower: probabilistic autoregressive dance generation with multimodal attention
- Multi-resolution partial differential equations preserved learning framework for spatiotemporal dynamics
- CFN-ESA: A Cross-Modal Fusion Network with Emotion-Shift Awareness for Dialogue Emotion Recognition
- Deep Instance Segmentation with Automotive Radar Detection Points
- HiCMAE: Hierarchical Contrastive Masked Autoencoder for Self-Supervised Audio-Visual Emotion Recognition
- A newcomer's guide to deep learning for inverse design in nano-photonics
- IA-RED: Interpretability-Aware Redundancy Reduction for Vision Transformers
- PhenoBench -- A Large Dataset and Benchmarks for Semantic Image Interpretation in the Agricultural Domain
- Efficacy of Transformer Networks for Classification of Raw EEG Data
- Merak: An Efficient Distributed DNN Training Framework with Automated 3D Parallelism for Giant Foundation Models
- Improving Video-Text Retrieval by Multi-Stream Corpus Alignment and Dual Softmax Loss
- Towards Accurate Post-Training Quantization for Vision Transformer
- Large Kernel Distillation Network for Efficient Single Image Super-Resolution
- Entropy-based Logic Explanations of Neural Networks
- End-to-End Video Instance Segmentation with Transformers
- Training Data Influence Analysis and Estimation: A Survey
- RepMLP: Re-parameterizing Convolutions into Fully-connected Layers for Image Recognition
- SwinVRNN: A Data-Driven Ensemble Forecasting Model via Learned Distribution Perturbation
- ModeT: Learning Deformable Image Registration via Motion Decomposition Transformer
- Adaptive Mixture of Experts Learning for Generalizable Face Anti-Spoofing
- Rethinking Scanning Strategies with Vision Mamba in Semantic Segmentation of Remote Sensing Imagery: An Experimental Study
- Partial success in closing the gap between human and machine vision
- CNN-LSTM and Transfer Learning Models for Malware Classification based on Opcodes and API Calls
- RoadFormer: Duplex Transformer for RGB-Normal Semantic Road Scene Parsing
- Tomato Maturity Recognition with Convolutional Transformers
- AstroCLIP: A Cross-Modal Foundation Model for Galaxies
- Transformers in Self-Supervised Monocular Depth Estimation with Unknown Camera Intrinsics
- ASFormer: Transformer for Action Segmentation
- ConvTransformer: A Convolutional Transformer Network for Video Frame Synthesis
- Exploring the Synergies of Hybrid CNNs and ViTs Architectures for Computer Vision: A survey
- Improving deep neural network generalization and robustness to background bias via layer-wise relevance propagation optimization
- BYOL for Audio: Exploring Pre-trained General-purpose Audio Representations
- Bidirectional Generation of Structure and Properties Through a Single Molecular Foundation Model
- You Only Train Once: Learning a General Anomaly Enhancement Network with Random Masks for Hyperspectral Anomaly Detection
- CMT: Convolutional Neural Networks Meet Vision Transformers
- A simple linear algebra identity to optimize Large-Scale Neural Network Quantum States
- TopicFM: Robust and Interpretable Topic-Assisted Feature Matching
- Scale Efficiently: Insights from Pre-training and Fine-tuning Transformers
- Factorizer: A Scalable Interpretable Approach to Context Modeling for Medical Image Segmentation
- CoTr: Efficiently Bridging CNN and Transformer for 3D Medical Image Segmentation
- TFPose: Direct Human Pose Estimation with Transformers
- T-former: An Efficient Transformer for Image Inpainting
- Space-time Mixing Attention for Video Transformer
- Breast Cancer Histopathology Image based Gene Expression Prediction using Spatial Transcriptomics data and Deep Learning
- A Comprehensive Survey on Hardware-Aware Neural Architecture Search
- VST++: Efficient and Stronger Visual Saliency Transformer
- Multiscale Vision Transformers
- SOLQ: Segmenting Objects by Learning Queries
- Enhancing Skin Disease Classification Leveraging Transformer-based Deep Learning Architectures and Explainable AI
- MERLOT: Multimodal Neural Script Knowledge Models
- Lightweight Pixel Difference Networks for Efficient Visual Representation Learning
- Vision Transformers Need Registers
- How to train your ViT? Data, Augmentation, and Regularization in Vision Transformers
- Domain generalization in deep learning-based mass detection in mammography: A large-scale multi-center study
- ISTR: End-to-End Instance Segmentation with Transformers
- Vision Transformer Pruning
- Vision-Language Models for Edge Networks: A Comprehensive Survey
- Line as a Visual Sentence: Context-aware Line Descriptor for Visual Localization
- Toward Interpretable Sleep Stage Classification Using Cross-Modal Transformers
- Feature Completion Transformer for Occluded Person Re-identification
- Towards Holistic Surgical Scene Understanding
- SODFormer: Streaming Object Detection with Transformer Using Events and Frames
- Prediction of transonic flow over supercritical airfoils using geometric-encoding and deep-learning strategies
- Depth-Wise Convolutions in Vision Transformers for Efficient Training on Small Datasets
- Graph-MLP: Node Classification without Message Passing in Graph
- Embrace Limited and Imperfect Training Datasets: Opportunities and Challenges in Plant Disease Recognition Using Deep Learning
- MCUNetV2: Memory-Efficient Patch-based Inference for Tiny Deep Learning
- Convolutional Fine-Grained Classification with Self-Supervised Target Relation Regularization
- Luna: Linear Unified Nested Attention
- Development of Skip Connection in Deep Neural Networks for Computer Vision and Medical Image Analysis: A Survey
- Point-BERT: Pre-training 3D Point Cloud Transformers with Masked Point Modeling
- Ensemble of Averages: Improving Model Selection and Boosting Performance in Domain Generalization
- Scaling Spike-driven Transformer with Efficient Spike Firing Approximation Training
- FengWu: Pushing the Skillful Global Medium-range Weather Forecast beyond 10 Days Lead
- M6: A Chinese Multimodal Pretrainer
- LMFNet: An Efficient Multimodal Fusion Approach for Semantic Segmentation in High-Resolution Remote Sensing
- Towards Evaluating Explanations of Vision Transformers for Medical Imaging
- A Survey on State-of-the-art Deep Learning Applications and Challenges
- Detecting Dementia from Speech and Transcripts using Transformers
- LLM-FP4: 4-Bit Floating-Point Quantized Transformers
- Transformer Encoder with Multiscale Deep Learning for Pain Classification Using Physiological Signals
- The Free Energy Principle for Perception and Action: A Deep Learning Perspective
- Automated Audio Captioning: An Overview of Recent Progress and New Challenges
- Adaptive Kalman-Informed Transformer
- GCoNet+: A Stronger Group Collaborative Co-Salient Object Detector
- Cross-Forgery Analysis of Vision Transformers and CNNs for Deepfake Image Detection
- Image Classification with Small Datasets: Overview and Benchmark
- Face Transformer for Recognition
- A Transformer-based Generative Adversarial Network for Brain Tumor Segmentation
- Vision Transformers on the Edge: A Comprehensive Survey of Model Compression and Acceleration Strategies
- FakeNews: GAN-based generation of realistic 3D volumetric data -- A systematic review and taxonomy
- SegTransVAE: Hybrid CNN -- Transformer with Regularization for medical image segmentation
- SurvTRACE: Transformers for Survival Analysis with Competing Events
- Adaptive Patch Contrast for Weakly Supervised Semantic Segmentation
- PPT Fusion: Pyramid Patch Transformerfor a Case Study in Image Fusion
- Knowledge-based Deep Learning for Modeling Chaotic Systems
- W-Transformers : A Wavelet-based Transformer Framework for Univariate Time Series Forecasting
- Deep Weakly-Supervised Learning Methods for Classification and Localization in Histology Images: A Survey
- Towards an astronomical foundation model for stars with a Transformer-based model
- A Comprehensive Review of Modern Object Segmentation Approaches
- A Survey on Occupancy Perception for Autonomous Driving: The Information Fusion Perspective
- COVID-VIT: Classification of COVID-19 from CT chest images based on vision transformer models
- FoodSAM: Any Food Segmentation
- Supervised Contrastive Learning for Multimodal Unreliable News Detection in COVID-19 Pandemic
- SpectralEarth: Training Hyperspectral Foundation Models at Scale
- CholecTriplet2022: Show me a tool and tell me the triplet -- an endoscopic vision challenge for surgical action triplet detection
- Vision Transformers with Patch Diversification
- An Attention Free Transformer
- A Tiny Transformer for Low-Power Arrhythmia Classification on Microcontrollers
- End-to-End Human Pose and Mesh Reconstruction with Transformers
- A Survey on Continual Semantic Segmentation: Theory, Challenge, Method and Application
- Deciphering the Language of Nature: A transformer-based language model for deleterious mutations in proteins
- Refiner: Refining Self-attention for Vision Transformers
- Deepfake Detection Scheme Based on Vision Transformer and Distillation
- Exploring Adapter-based Transfer Learning for Recommender Systems: Empirical Studies and Practical Insights
- Your Negative May not Be True Negative: Boosting Image-Text Matching with False Negative Elimination
- Multiscaled Multi-Head Attention-based Video Transformer Network for Hand Gesture Recognition
- End-to-end deep learning for directly estimating grape yield from ground-based imagery
- Self-supervised 3D anatomy segmentation using self-distilled masked image transformer (SMIT)
- Learning without Forgetting for Vision-Language Models
- Danish Fungi 2020 -- Not Just Another Image Recognition Dataset
- Challenges for Monocular 6D Object Pose Estimation in Robotics
- Ensembles of Vision Transformers as a New Paradigm for Automated Classification in Ecology
- Applications of artificial intelligence in the analysis of histopathology images of gliomas: a review
- Spectral-wise Implicit Neural Representation for Hyperspectral Image Reconstruction
- Computer-Aided Design as Language
- GSRFormer: Grounded Situation Recognition Transformer with Alternate Semantic Attention Refinement
- Show me your NFT and I tell you how it will perform: Multimodal representation learning for NFT selling price prediction
- Vilio: State-of-the-art Visio-Linguistic Models applied to Hateful Memes
- Patch is Enough: Naturalistic Adversarial Patch against Vision-Language Pre-training Models
- Effectiveness Assessment of Recent Large Vision-Language Models
- Gaussian Radar Transformer for Semantic Segmentation in Noisy Radar Data
- Machine learning of microstructure--property relationships in materials leveraging microstructure representation from foundational vision transformers
- Pyramid Medical Transformer for Medical Image Segmentation
- Grafting Transformer on Automatically Designed Convolutional Neural Network for Hyperspectral Image Classification
- A Review on Low-Dose Emission Tomography Post-Reconstruction Denoising with Neural Network Approaches
- FlexMoE: Scaling Large-scale Sparse Pre-trained Model Training via Dynamic Device Placement
- Detecting Intentional AIS Shutdown in Open Sea Maritime Surveillance Using Self-Supervised Deep Learning
- Depth Awakens: A Depth-perceptual Attention Fusion Network for RGB-D Camouflaged Object Detection
- Optimizing Vision Transformers for Medical Image Segmentation
- Multimodal Parameter-Efficient Few-Shot Class Incremental Learning
- TransFusion: Cross-view Fusion with Transformer for 3D Human Pose Estimation
- Few-shot Action Recognition with Prototype-centered Attentive Learning
- Masked Transformer for image Anomaly Localization
- RockGPT: Reconstructing three-dimensional digital rocks from single two-dimensional slice from the perspective of video generation
- Contrastive Language-Vision AI Models Pretrained on Web-Scraped Multimodal Data Exhibit Sexual Objectification Bias
- SemantiCodec: An Ultra Low Bitrate Semantic Audio Codec for General Sound
- Revisiting Computer-Aided Tuberculosis Diagnosis
- Graph Neural Network contextual embedding for Deep Learning on Tabular Data
- CT-Net: Arbitrary-Shaped Text Detection via Contour Transformer
- PatrickStar: Parallel Training of Pre-trained Models via Chunk-based Memory Management
- LieTransformer: Equivariant self-attention for Lie Groups
- SpectralFormer: Rethinking Hyperspectral Image Classification with Transformers
- Exploring the Limits of Large Scale Pre-training
- SHaRPose: Sparse High-Resolution Representation for Human Pose Estimation
- CD-CTFM: A Lightweight CNN-Transformer Network for Remote Sensing Cloud Detection Fusing Multiscale Features
- Audio Transformers
- PSLT: A Light-weight Vision Transformer with Ladder Self-Attention and Progressive Shift
- Pruning vs XNOR-Net: A Comprehensive Study of Deep Learning for Audio Classification on Edge-devices
- Deep Semantic-Visual Alignment for Zero-Shot Remote Sensing Image Scene Classification
- Enhancing Network Initialization for Medical AI Models Using Large-Scale, Unlabeled Natural Images
- Glance-and-Gaze Vision Transformer
- Concurrent ischemic lesion age estimation and segmentation of CT brain using a Transformer-based network
- CiT-Net: Convolutional Neural Networks Hand in Hand with Vision Transformers for Medical Image Segmentation
- Gastrointestinal Disorder Detection with a Transformer Based Approach
- Multimodal Fusion and Vision-Language Models: A Survey for Robot Vision
- UP-DETR: Unsupervised Pre-training for Object Detection with Transformers
- Hanayo: Harnessing Wave-like Pipeline Parallelism for Enhanced Large Model Training Efficiency
- Transformer Network for Significant Stenosis Detection in CCTA of Coronary Arteries
- Unifying Two-Stream Encoders with Transformers for Cross-Modal Retrieval
- ShaDocNet: Learning Spatial-Aware Tokens in Transformer for Document Shadow Removal
- VIMPAC: Video Pre-Training via Masked Token Prediction and Contrastive Learning
- Deep learning based infrared small object segmentation: Challenges and future directions
- Audio Captioning Transformer
- Medical Transformer: Universal Brain Encoder for 3D MRI Analysis
- Deep learning for 3D human pose estimation and mesh recovery: A survey
- FaST-GShare: Enabling Efficient Spatio-Temporal GPU Sharing in Serverless Computing for Deep Learning Inference
- Fully Transformer Networks for Semantic Image Segmentation
- PeCo: Perceptual Codebook for BERT Pre-training of Vision Transformers
- Tesseract: Parallelize the Tensor Parallelism Efficiently
- Explainable Knowledge Distillation for On-device Chest X-Ray Classification
- Artificial Intelligence in Materials Science and Engineering: Current Landscape, Key Challenges, and Future Trajectorie
- Unsupervised Brain Anomaly Detection and Segmentation with Transformers
- K-Lane: Lidar Lane Dataset and Benchmark for Urban Roads and Highways
- IQAGPT: Image Quality Assessment with Vision-language and ChatGPT Models
- Anatomy-aware and acquisition-agnostic joint registration with SynthMorph
- LGViT: Dynamic Early Exiting for Accelerating Vision Transformer
- Few-Shot Segmentation via Cycle-Consistent Transformer
- Clinical Insights: A Comprehensive Review of Language Models in Medicine
- Tensor Normalization and Full Distribution Training
- TransformerFusion: Monocular RGB Scene Reconstruction using Transformers
- The Lottery Tickets Hypothesis for Supervised and Self-supervised Pre-training in Computer Vision Models
- MC-ViViT: Multi-branch Classifier-ViViT to detect Mild Cognitive Impairment in older adults using facial videos
- ClST: A Convolutional Transformer Framework for Automatic Modulation Recognition by Knowledge Distillation
- CLAMP: Prompt-based Contrastive Learning for Connecting Language and Animal Pose
- Sem2NeRF: Converting Single-View Semantic Masks to Neural Radiance Fields
- Weaving Attention U-net: A Novel Hybrid CNN and Attention-based Method for Organs-at-risk Segmentation in Head and Neck CT Images
- Beyond Geo-localization: Fine-grained Orientation of Street-view Images by Cross-view Matching with Satellite Imagery with Supplementary Materials
- CiMLoop: A Flexible, Accurate, and Fast Compute-In-Memory Modeling Tool
- ElasticTrainer: Speeding Up On-Device Training with Runtime Elastic Tensor Selection
- Single-Shot Motion Completion with Transformer
- FreeREA: Training-Free Evolution-based Architecture Search
- Rethinking Domain Generalization: Discriminability and Generalizability
- Generating Comprehensive Lithium Battery Charging Data with Generative AI
- Hierarchical Vision Transformers for Cardiac Ejection Fraction Estimation
- SVFAP: Self-supervised Video Facial Affect Perceiver
- MATIS: Masked-Attention Transformers for Surgical Instrument Segmentation
- A Neural Network Transformer Model for Composite Microstructure Homogenization
- Improving the Detection of Small Oriented Objects in Aerial Images
- QMaxViT-Unet+: A Query-Based MaxViT-Unet with Edge Enhancement for Scribble-Supervised Segmentation of Medical Images
- Masked Particle Modeling on Sets: Towards Self-Supervised High Energy Physics Foundation Models
- SoccerNet 2023 Challenges Results
- Improving 360 Monocular Depth Estimation via Non-local Dense Prediction Transformer and Joint Supervised and Self-supervised Learning
- Prot2Text: Multimodal Protein's Function Generation with GNNs and Transformers
- Learning Vision-Guided Quadrupedal Locomotion End-to-End with Cross-Modal Transformers
- Vision Transformer for COVID-19 CXR Diagnosis using Chest X-ray Feature Corpus
- P2AT: Pyramid Pooling Axial Transformer for Real-time Semantic Segmentation
- A Video Is Worth Three Views: Trigeminal Transformers for Video-based Person Re-identification
- One Proxy Device Is Enough for Hardware-Aware Neural Architecture Search
- Adaptive Fourier Neural Operators: Efficient Token Mixers for Transformers
- Soft Sensing Transformer: Hundreds of Sensors are Worth a Single Word
- Self-Supervised Neuron Segmentation with Multi-Agent Reinforcement Learning
- A Convolutional Vision Transformer for Semantic Segmentation of Side-Scan Sonar Data
- CgT-GAN: CLIP-guided Text GAN for Image Captioning
- Improving deep learning with prior knowledge and cognitive models: A survey on enhancing explainability, adversarial robustness and zero-shot learning
- Drastic Circuit Depth Reductions with Preserved Adversarial Robustness by Approximate Encoding for Quantum Machine Learning
- Delving Globally into Texture and Structure for Image Inpainting
- Efficient Quantized Sparse Matrix Operations on Tensor Cores
- Transformer-Based Model for Monocular Visual Odometry: A Video Understanding Approach
- Re-Scoring Using Image-Language Similarity for Few-Shot Object Detection
- Density-based clustering with fully-convolutional networks for crowd flow detection from drones
- Derm-T2IM: Harnessing Synthetic Skin Lesion Data via Stable Diffusion Models for Enhanced Skin Disease Classification using ViT and CNN
- BrainNPT: Pre-training of Transformer networks for brain network classification
- Foldsformer: Learning Sequential Multi-Step Cloth Manipulation With Space-Time Attention
- Evolving Modular Soft Robots without Explicit Inter-Module Communication using Local Self-Attention
- Enhancing MRI-Based Classification of Alzheimer's Disease with Explainable 3D Hybrid Compact Convolutional Transformers
- Assaying Out-Of-Distribution Generalization in Transfer Learning
- CT-Mamba: A Hybrid Convolutional State Space Model for Low-Dose CT Denoising
- MultiScale Probability Map guided Index Pooling with Attention-based learning for Road and Building Segmentation
- Deep Learning Technique for Human Parsing: A Survey and Outlook
- ConvMLP: Hierarchical Convolutional MLPs for Vision
- Vision Permutator: A Permutable MLP-Like Architecture for Visual Recognition
- Exploiting Shape Cues for Weakly Supervised Semantic Segmentation
- Seeing Out of tHe bOx: End-to-End Pre-training for Vision-Language Representation Learning
- Towards Sim-to-Real Industrial Parts Classification with Synthetic Dataset
- Evaluating Pre-trained Convolutional Neural Networks and Foundation Models as Feature Extractors for Content-based Medical Image Retrieval
- MADRL-Based Rate Adaptation for 360° Video Streaming with Multi-Viewpoint Prediction
- Transfer Learning Framework for Low-Resource Text-to-Speech using a Large-Scale Unlabeled Speech Corpus
- MetaSegNet: Metadata-collaborative Vision-Language Representation Learning for Semantic Segmentation of Remote Sensing Images
- RPLHR-CT Dataset and Transformer Baseline for Volumetric Super-Resolution from CT Scans
- ITA: An Energy-Efficient Attention and Softmax Accelerator for Quantized Transformers
- TVT: Transferable Vision Transformer for Unsupervised Domain Adaptation
- Facial Action Unit Detection by Adaptively Constraining Self-Attention and Causally Deconfounding Sample
- Deep Learning-based Bathymetry Retrieval without In-situ Depths using Remote Sensing Imagery and SfM-MVS DSMs with Data Gaps
- Multi-modal land cover mapping of remote sensing images using pyramid attention and gated fusion networks
- Self-supervised visual learning in the low-data regime: a comparative evaluation
- Data Movement Is All You Need: A Case Study on Optimizing Transformers
- Vision-Language Modeling Meets Remote Sensing: Models, Datasets and Perspectives
- Rethinking Object Saliency Ranking: A Novel Whole-flow Processing Paradigm
- Safe-VLN: Collision Avoidance for Vision-and-Language Navigation of Autonomous Robots Operating in Continuous Environments
- Embedded Visual Prompt Tuning
- Ultra-High-Resolution Detector Simulation with Intra-Event Aware GAN and Self-Supervised Relational Reasoning
- Supervised Transfer Learning at Scale for Medical Imaging
- MCTNet: A Multi-Scale CNN-Transformer Network for Change Detection in Optical Remote Sensing Images
- STB-VMM: Swin Transformer Based Video Motion Magnification
- Meta-Learning Symmetries by Reparameterization
- Graph Convolutional Networks based on Manifold Learning for Semi-Supervised Image Classification
- Vision Transformers for Small Histological Datasets Learned through Knowledge Distillation
- Multi-Head Self-Attention via Vision Transformer for Zero-Shot Learning
- VOLO: Vision Outlooker for Visual Recognition
- Spectrum-driven Mixed-frequency Network for Hyperspectral Salient Object Detection
- ElegansNet: a brief scientific report and initial experiments
- CosSIF: Cosine similarity-based image filtering to overcome low inter-class variation in synthetic medical image datasets
- Deep Learning for Pancreas Segmentation: a Systematic Review
- Distillation-based fabric anomaly detection
- Less is More: Consistent Video Depth Estimation with Masked Frames Modeling
- Revisiting Model Stitching to Compare Neural Representations
- RAIN: RegulArization on Input and Network for Black-Box Domain Adaptation
- Salient Mask-Guided Vision Transformer for Fine-Grained Classification
- Representation Matters: Offline Pretraining for Sequential Decision Making
- Exploiting the Generative Adversarial Network Approach to Create a Synthetic Topography Corneal Image
- A Semantic and Motion-Aware Spatiotemporal Transformer Network for Action Detection
- Neural network fragile watermarking with no model performance degradation
- Towards a Smaller Student: Capacity Dynamic Distillation for Efficient Image Retrieval
- Cross-View Visual Geo-Localization for Outdoor Augmented Reality
- CLIP-ReIdent: Contrastive Training for Player Re-Identification
- A Full Transformer-based Framework for Automatic Pain Estimation using Videos
- TranSOP: Transformer-based Multimodal Classification for Stroke Treatment Outcome Prediction
- Significantly improving zero-shot X-ray pathology classification via fine-tuning pre-trained image-text encoders
- Noise2Image: Noise-Enabled Static Scene Recovery for Event Cameras
- Colossal-AI: A Unified Deep Learning System For Large-Scale Parallel Training
- Dataset Distillation with Infinitely Wide Convolutional Networks
- Pure Transformer with Integrated Experts for Scene Text Recognition
- DuDoTrans: Dual-Domain Transformer Provides More Attention for Sinogram Restoration in Sparse-View CT Reconstruction
- PSViT: Better Vision Transformer via Token Pooling and Attention Sharing
- Boosting EfficientNets Ensemble Performance via Pseudo-Labels and Synthetic Images by pix2pixHD for Infection and Ischaemia Classification in Diabetic Foot Ulcers
- Classification of Adventitious Sounds Combining Cochleogram and Vision Transformers
- SF2Former: Amyotrophic Lateral Sclerosis Identification From Multi-center MRI Data Using Spatial and Frequency Fusion Transformer
- EVREAL: Towards a Comprehensive Benchmark and Analysis Suite for Event-based Video Reconstruction
- A Unified Survey on Anomaly, Novelty, Open-Set, and Out-of-Distribution Detection: Solutions and Future Challenges
- ELEV-VISION-SAM: Integrated Vision Language and Foundation Model for Automated Estimation of Building Lowest Floor Elevation
- Multi-Scale Hybrid Vision Transformer for Learning Gastric Histology: AI-Based Decision Support System for Gastric Cancer Treatment
- Super-Resolution Radar Imaging with Sparse Arrays Using a Deep Neural Network Trained with Enhanced Virtual Data
- EDMAE: An Efficient Decoupled Masked Autoencoder for Standard View Identification in Pediatric Echocardiography
- TEMGNet: Deep Transformer-based Decoding of Upperlimb sEMG for Hand Gestures Recognition
- MambaMIM: Pre-training Mamba with State Space Token Interpolation and its Application to Medical Image Segmentation
- Centroid Transformers: Learning to Abstract with Attention
- deep-significance - Easy and Meaningful Statistical Significance Testing in the Age of Neural Networks
- Painterly Image Harmonization using Diffusion Model
- Federated Split Vision Transformer for COVID-19 CXR Diagnosis using Task-Agnostic Training
- Emotion Separation and Recognition from a Facial Expression by Generating the Poker Face with Vision Transformers
- Exploring Advances in Transformers and CNN for Skin Lesion Diagnosis on Small Datasets
- First-Generation Inference Accelerator Deployment at Facebook
- PolSAR Image Classification using a Hybrid Complex-Valued Network (HybridCVNet)
- Classification of lung cancer subtypes on CT images with synthetic pathological priors
- TokenPose: Learning Keypoint Tokens for Human Pose Estimation
- Accelerating Phase Field Simulations Through a Hybrid Adaptive Fourier Neural Operator with U-Net Backbone
- Predicting Information Pathways Across Online Communities
- HRPVT: High-Resolution Pyramid Vision Transformer for medium and small-scale human pose estimation
- TransEM:Residual Swin-Transformer based regularized PET image reconstruction
- Global Filter Networks for Image Classification
- LT-ViT: A Vision Transformer for multi-label Chest X-ray classification
- Unsupervised Multivariate Time-Series Transformers for Seizure Identification on EEG
- One never walks alone: the effect of the perturber population on subhalo measurements in strong gravitational lenses
- DMTNet: Dynamic Multi-scale Network for Dual-pixel Images Defocus Deblurring with Transformer
- Streamlined Global and Local Features Combinator (SGLC) for High Resolution Image Dehazing
- BodyFormer: Semantics-guided 3D Body Gesture Synthesis with Transformer
- SurgiTrack: Fine-Grained Multi-Class Multi-Tool Tracking in Surgical Videos
- Dilated convolution with learnable spacings
- EVJVQA Challenge: Multilingual Visual Question Answering
- GLIMS: Attention-Guided Lightweight Multi-Scale Hybrid Network for Volumetric Semantic Segmentation
- PTNet: A High-Resolution Infant MRI Synthesizer Based on Transformer
- Multi-task Learning for Radar Signal Characterisation
- Reliable Object Tracking by Multimodal Hybrid Feature Extraction and Transformer-Based Fusion
- Scaling up DNA digital data storage by efficiently predicting DNA hybridisation using deep learning
- Building Blocks for a Complex-Valued Transformer Architecture
- Homogeneous Tokenizer Matters: Homogeneous Visual Tokenizer for Remote Sensing Image Understanding
- STAR: Sparse Transformer-based Action Recognition
- Fully Transformer-Equipped Architecture for End-to-End Referring Video Object Segmentation
- MHFormer: Multi-Hypothesis Transformer for 3D Human Pose Estimation
- Image and Model Transformation with Secret Key for Vision Transformer
- BenthicNet: A global compilation of seafloor images for deep learning applications
- OH-Former: Omni-Relational High-Order Transformer for Person Re-Identification
- Hierarchical Interdisciplinary Topic Detection Model for Research Proposal Classification
- Predicting Knee Osteoarthritis Progression from Structural MRI using Deep Learning
- Sparse Transformer with Local and Seasonal Adaptation for Multivariate Time Series Forecasting
- CovidExpert: A Triplet Siamese Neural Network framework for the detection of COVID-19
- Vision Transformers: From Semantic Segmentation to Dense Prediction
- Transformer-based Context Condensation for Boosting Feature Pyramids in Object Detection
- Trajformer: Trajectory Prediction with Local Self-Attentive Contexts for Autonomous Driving
- Controllable Generation with Text-to-Image Diffusion Models: A Survey
- EDNet: Edge-Optimized Small Target Detection in UAV Imagery -- Faster Context Attention, Better Feature Fusion, and Hardware Acceleration
- Language Modelling with Pixels
- Semi-Supervised Coupled Thin-Plate Spline Model for Rotation Correction and Beyond
- Performance of externally validated machine learning models based on histopathology images for the diagnosis, classification, prognosis, or treatment outcome prediction in female breast cancer: A systematic review
- Zero-Shot Text-Guided Object Generation with Dream Fields
- Towards Safer Robot-Assisted Surgery: A Markerless Augmented Reality Framework
- Pose2Trajectory: Using Transformers on Body Pose to Predict Tennis Player's Trajectory
- Coordination Among Neural Modules Through a Shared Global Workspace
- A Bayesian Deep Learning Approach to Near-Term Climate Prediction
- Transformer with Selective Shuffled Position Embedding and Key-Patch Exchange Strategy for Early Detection of Knee Osteoarthritis
- Rethinking Cross-Domain Pedestrian Detection: A Background-Focused Distribution Alignment Framework for Instance-Free One-Stage Detectors
- Finding Strong Gravitational Lenses Through Self-Attention
- MORE: A Multimodal Object-Entity Relation Extraction Dataset with a Benchmark Evaluation
- Generative Adversarial Transformers
- Large Scale Visual Food Recognition
- ASiT: Local-Global Audio Spectrogram vIsion Transformer for Event Classification
- Human-Object Interaction Prediction in Videos through Gaze Following
- A Vision Transformer Approach for Efficient Near-Field Irregular SAR Super-Resolution
- Synthesized Speech Detection Using Convolutional Transformer-Based Spectrogram Analysis
- ThermoPore: Predicting Part Porosity Based on Thermal Images Using Deep Learning
- HeadPosr: End-to-end Trainable Head Pose Estimation using Transformer Encoders
- Hybrid Quantum Vision Transformers for Event Classification in High Energy Physics
- PipeTransformer: Automated Elastic Pipelining for Distributed Training of Transformers
- HST-MRF: Heterogeneous Swin Transformer with Multi-Receptive Field for Medical Image Segmentation
- The Deep Bootstrap Framework: Good Online Learners are Good Offline Generalizers
- StARformer: Transformer with State-Action-Reward Representations for Visual Reinforcement Learning
- Minimax Active Learning
- Scopeformer: n-CNN-ViT Hybrid Model for Intracranial Hemorrhage Classification
- Accurate identification and measurement of the precipitate area by two-stage deep neural networks in novel chromium-based alloys
- Energy-Efficient Fast Object Detection on Edge Devices for IoT Systems
- Attention Aided CSI Wireless Localization
- Exploiting Temporal Contexts with Strided Transformer for 3D Human Pose Estimation
- Astroconformer: The Prospects of Analyzing Stellar Light Curves with Transformer-Based Deep Learning Models
- From Pretraining to Privacy: Federated Ultrasound Foundation Model with Self-Supervised Learning
- Dual-Modal Attention-Enhanced Text-Video Retrieval with Triplet Partial Margin Contrastive Learning
- Visual Attention Prompted Prediction and Learning
- Hformer: Hybrid CNN-Transformer for Fringe Order Prediction in Phase Unwrapping of Fringe Projection
- Evaluating histopathology transfer learning with ChampKit
- Proposal Relation Network for Temporal Action Detection
- Towards Unsupervised Domain Adaptation via Domain-Transformer
- Enhancing the vision-language foundation model with key semantic knowledge-emphasized report refinement
- Attention-aware Semantic Communications for Collaborative Inference
- Multimodal Detection of Unknown Objects on Roads for Autonomous Driving
- Multi-Compound Transformer for Accurate Biomedical Image Segmentation
- Does CLIP Know My Face?
- Foundation Models and Transformers for Anomaly Detection: A Survey
- PRSeg: A Lightweight Patch Rotate MLP Decoder for Semantic Segmentation
- ProTo: Program-Guided Transformer for Program-Guided Tasks
- Architecture-Preserving Provable Repair of Deep Neural Networks
- Rethinking Cooking State Recognition with Vision Transformers
- Operator Learning with Neural Fields: Tackling PDEs on General Geometries
- Anatomically aware dual-hop learning for pulmonary embolism detection in CT pulmonary angiograms
- VT-ADL: A Vision Transformer Network for Image Anomaly Detection and Localization
- UniNeXt: Exploring A Unified Architecture for Vision Recognition
- OnDev-LCT: On-Device Lightweight Convolutional Transformers towards federated learning
- Robust Multiview Multimodal Driver Monitoring System Using Masked Multi-Head Self-Attention
- Vid2Seq: Large-Scale Pretraining of a Visual Language Model for Dense Video Captioning
- Inductive Biases and Variable Creation in Self-Attention Mechanisms
- Uncovering local aggregated air quality index with smartphone captured images leveraging efficient deep convolutional neural network
- Diffusion Based Augmentation for Captioning and Retrieval in Cultural Heritage
- Transfer Learning Gaussian Anomaly Detection by Fine-tuning Representations
- Joint calibration and mapping of satellite altimetry data using trainable variational models
- A Dual Semantic-Aware Recurrent Global-Adaptive Network For Vision-and-Language Navigation
- Diverse Image Inpainting with Bidirectional and Autoregressive Transformers
- Enhancing Deepfake Detection using SE Block Attention with CNN
- Self-supervised Image-text Pre-training With Mixed Data In Chest X-rays
- HAT: Hierarchical Aggregation Transformers for Person Re-identification
- A vision transformer-based framework for knowledge transfer from multi-modal to mono-modal lymphoma subtyping models
- GiT: Graph Interactive Transformer for Vehicle Re-identification
- Exploiting Transformer in Sparse Reward Reinforcement Learning for Interpretable Temporal Logic Motion Planning
- Twins-PainViT: Towards a Modality-Agnostic Vision Transformer Framework for Multimodal Automatic Pain Assessment using Facial Videos and fNIRS
- Exploring the Landscape of Ubiquitous In-home Health Monitoring: A Comprehensive Survey
- Power-LLaVA: Large Language and Vision Assistant for Power Transmission Line Inspection
- EfficientPhys: Enabling Simple, Fast and Accurate Camera-Based Vitals Measurement
- Joint Learning Content and Degradation Aware Feature for Blind Super-Resolution
- RTQ: Rethinking Video-language Understanding Based on Image-text Model
- Relative Positional Encoding for Transformers with Linear Complexity
- Automatic Differentiation-based Full Waveform Inversion with Flexible Workflows
- Self-Supervised Learning for Medical Image Data with Anatomy-Oriented Imaging Planes
- Sinkformers: Transformers with Doubly Stochastic Attention
- MultiMAE-DER: Multimodal Masked Autoencoder for Dynamic Emotion Recognition
- TransVOS: Video Object Segmentation with Transformers
- A Survey of Multimodal Sarcasm Detection
- Tile Classification Based Viewport Prediction with Multi-modal Fusion Transformer
- Simpler is Better: Few-shot Semantic Segmentation with Classifier Weight Transformer
- Comparative and Interpretative Analysis of CNN and Transformer Models in Predicting Wildfire Spread Using Remote Sensing Data
- Denoising of 3D MR images using a voxel-wise hybrid residual MLP-CNN model to improve small lesion diagnostic confidence
- Effective End-to-End Vision Language Pretraining with Semantic Visual Loss
- Your "Attention" Deserves Attention: A Self-Diversified Multi-Channel Attention for Facial Action Analysis
- Fast and Accurate Single-Image Depth Estimation on Mobile Devices, Mobile AI 2021 Challenge: Report
- Kaleido-BERT: Vision-Language Pre-training on Fashion Domain
- Dual-Task Vision Transformer for Rapid and Accurate Intracerebral Hemorrhage CT Image Classification
- Dual-interest Factorization-heads Attention for Sequential Recommendation
- Convolution-enhanced Evolving Attention Networks
- A Dual-Stream Recurrence-Attention Network With Global-Local Awareness for Emotion Recognition in Textual Dialog
- PU-Transformer: Point Cloud Upsampling Transformer
- AliMe MKG: A Multi-modal Knowledge Graph for Live-streaming E-commerce
- MultiCapCLIP: Auto-Encoding Prompts for Zero-Shot Multilingual Visual Captioning
- Unifying Global-Local Representations in Salient Object Detection with Transformer
- Understanding the computational demands underlying visual reasoning
- Axial multi-layer perceptron architecture for automatic segmentation of choroid plexus in multiple sclerosis
- CoSformer: Detecting Co-Salient Object with Transformers
- Novelty Detection and Analysis of Traffic Scenario Infrastructures in the Latent Space of a Vision Transformer-Based Triplet Autoencoder
- Sam2Rad: A Segmentation Model for Medical Images with Learnable Prompts
- SSFG: Stochastically Scaling Features and Gradients for Regularizing Graph Convolutional Networks
- Fast Convergence of DETR with Spatially Modulated Co-Attention
- Pipeline Parallelism for Inference on Heterogeneous Edge Computing
- Spatio-temporal Prompting Network for Robust Video Feature Extraction
- Learning Motion and Temporal Cues for Unsupervised Video Object Segmentation
- PECI-Net: Bolus segmentation from video fluoroscopic swallowing study images using preprocessing ensemble and cascaded inference
- MECKD: Deep Learning-Based Fall Detection in Multilayer Mobile Edge Computing With Knowledge Distillation
- Multi-modal Extreme Classification
- Regress Before Construct: Regress Autoencoder for Point Cloud Self-supervised Learning
- Polar-Net: A Clinical-Friendly Model for Alzheimer's Disease Detection in OCTA Images
- ClipCap: CLIP Prefix for Image Captioning
- IFShip: Interpretable Fine-grained Ship Classification with Domain Knowledge-Enhanced Vision-Language Models
- Expert-LaSTS: Expert-Knowledge Guided Latent Space for Traffic Scenarios
- Large-vocabulary forensic pathological analyses via prototypical cross-modal contrastive learning
- Mpox-AISM: AI-Mediated Super Monitoring for Mpox and Like-Mpox
- Multi-Modal Learning for AU Detection Based on Multi-Head Fused Transformers
- Rethinking model prototyping through the MedMNIST+ dataset collection
- Spatial-aware Transformer-GRU Framework for Enhanced Glaucoma Diagnosis from 3D OCT Imaging
- Tiny Transformers for Environmental Sound Classification at the Edge
- TokenLearner: What Can 8 Learned Tokens Do for Images and Videos?
- Exploring Masked Autoencoders for Sensor-Agnostic Image Retrieval in Remote Sensing
- Robust Mutual Learning for Semi-supervised Semantic Segmentation
- ROI-Aware Multiscale Cross-Attention Vision Transformer for Pest Image Identification
- Vision Xformers: Efficient Attention for Image Classification
- MM-ALT: A Multimodal Automatic Lyric Transcription System
- Focused Decoding Enables 3D Anatomical Detection by Transformers
- Dynamic Feature Regularized Loss for Weakly Supervised Semantic Segmentation
- Uformer-ICS: A U-Shaped Transformer for Image Compressive Sensing Service
- Histopathological Image Classification based on Self-Supervised Vision Transformer and Weak Labels
- Topological Planning with Transformers for Vision-and-Language Navigation
- Federated Learning for Chronic Obstructive Pulmonary Disease Classification with Partial Personalized Attention Mechanism
- Visual Transformers for Primates Classification and Covid Detection
- Weakly Supervised Intracranial Hemorrhage Segmentation using Head-Wise Gradient-Infused Self-Attention Maps from a Swin Transformer in Categorical Learning
- DaFoEs: Mixing Datasets towards the generalization of vision-state deep-learning Force Estimation in Minimally Invasive Robotic Surgery
- NAC-TCN: Temporal Convolutional Networks with Causal Dilated Neighborhood Attention for Emotion Understanding
- A Review of Deep Learning Approaches for Non-Invasive Cognitive Impairment Detection
- Human Motion Video Generation: A Survey
- Transformer-based Fusion of 2D-pose and Spatio-temporal Embeddings for Distracted Driver Action Recognition
- Generating Image Adversarial Examples by Embedding Digital Watermarks
- MMMNA-Net for Overall Survival Time Prediction of Brain Tumor Patients
- MetaCVR: Conversion Rate Prediction via Meta Learning in Small-Scale Recommendation Scenarios
- Test-Time Personalization with a Transformer for Human Pose Estimation
- Improving 3D Object Detection with Channel-wise Transformer
- TopoTxR: A topology-guided deep convolutional network for breast parenchyma learning on DCE-MRIs
- Low Precision Decentralized Distributed Training over IID and non-IID Data
- Hyperbolic Deep Neural Networks: A Survey
- Visual-Semantic Transformer for Scene Text Recognition
- Tightly Coupled Learning Strategy for Weakly Supervised Hierarchical Place Recognition
- The Training Process of Many Deep Networks Explores the Same Low-Dimensional Manifold
- Dataset balancing can hurt model performance
- OffRoadTranSeg: Semi-Supervised Segmentation using Transformers on OffRoad environments
- Operating critical machine learning models in resource constrained regimes
- Radar Velocity Transformer: Single-scan Moving Object Segmentation in Noisy Radar Point Clouds
- TransCT: Dual-path Transformer for Low Dose Computed Tomography
- Beyond the Eye: A Relational Model for Early Dementia Detection Using Retinal OCTA Images
- Transformers predicting the future. Applying attention in next-frame and time series forecasting
- Densely connected normalizing flows
- Rank Flow Embedding for Unsupervised and Semi-Supervised Manifold Learning
- Forensic Analysis and Localization of Multiply Compressed MP3 Audio Using Transformers
- RankNEAT: Outperforming Stochastic Gradient Search in Preference Learning Tasks
- UFO-ViT: High Performance Linear Vision Transformer without Softmax
- Eformer: Edge Enhancement based Transformer for Medical Image Denoising
- Softmax-free Linear Transformers
- The Low-Rank Simplicity Bias in Deep Networks
- Achieve Fairness without Demographics for Dermatological Disease Diagnosis
- Detecting Gender Bias in Transformer-based Models: A Case Study on BERT
- Augmenting Decompiler Output with Learned Variable Names and Types
- On Improving Adversarial Transferability of Vision Transformers
- Rad4XCNN: a new agnostic method for post-hoc global explanation of CNN-derived features by means of radiomics
- Unified Classification and Rejection: A One-versus-All Framework
- Cloud-based XAI Services for Assessing Open Repository Models Under Adversarial Attacks
- Shunted Self-Attention via Multi-Scale Token Aggregation
- A multimodal deep learning architecture for smoking detection with a small data approach
- TransMed: Transformers Advance Multi-modal Medical Image Classification
- Learning Fair Face Representation With Progressive Cross Transformer
- The Sensory Neuron as a Transformer: Permutation-Invariant Neural Networks for Reinforcement Learning
- Cooperative Multi-Agent Transfer Learning with Level-Adaptive Credit Assignment
- Scalable Imaginary Time Evolution with Neural Network Quantum States
- End-to-End Trainable Multi-Instance Pose Estimation with Transformers
- MOCHA: Real-Time Motion Characterization via Context Matching
- Reconstructing Three-decade Global Fine-Grained Nighttime Light Observations by a New Super-Resolution Framework
- TRIG: Transformer-Based Text Recognizer with Initial Embedding Guidance
- A SSIM Guided cGAN Architecture For Clinically Driven Generative Image Synthesis of Multiplexed Spatial Proteomics Channels
- Fus-MAE: A cross-attention-based data fusion approach for Masked Autoencoders in remote sensing
- Identifying the Defective: Detecting Damaged Grains for Cereal Appearance Inspection
- Leveraging Labelled Data Knowledge: A Cooperative Rectification Learning Network for Semi-supervised 3D Medical Image Segmentation
- Patch Slimming for Efficient Vision Transformers
- Evolving Attention with Residual Convolutions
- Transforming Agency. On the mode of existence of Large Language Models
- Data-Efficient Vision Transformers for Multi-Label Disease Classification on Chest Radiographs
- Fast MRI Reconstruction via Edge Attention
- Distinguishing a planetary transit from false positives: a Transformer-based classification for planetary transit signals
- TaylorShift: Shifting the Complexity of Self-Attention from Squared to Linear (and Back) using Taylor-Softmax
- Fusing Domain-Specific Content from Large Language Models into Knowledge Graphs for Enhanced Zero Shot Object State Classification
- IconQA: A New Benchmark for Abstract Diagram Understanding and Visual Language Reasoning
- Hardware Beyond Backpropagation: a Photonic Co-Processor for Direct Feedback Alignment
- Multimodal Interactive Lung Lesion Segmentation: A Framework for Annotating PET/CT Images based on Physiological and Anatomical Cues
- SDNet: mutil-branch for single image deraining using swin
- TDANet: Target-Directed Attention Network For Object-Goal Visual Navigation With Zero-Shot Ability
- Hard-Attention for Scalable Image Classification
- Rethinking Polyp Segmentation from an Out-of-Distribution Perspective
- Discrete Representations Strengthen Vision Transformer Robustness
- Vision And Text Transformer For Predicting Answerability On Visual Question Answering
- HIH: Towards More Accurate Face Alignment via Heatmap in Heatmap
- CATFace: Cross-Attribute-Guided Transformer with Self-Attention Distillation for Low-Quality Face Recognition
- Edge Devices Inference Performance Comparison
- Diffusion-Augmented Depth Prediction with Sparse Annotations
- Learning Visual Abstract Reasoning through Dual-Stream Networks
- OmniNet: Omnidirectional Representations from Transformers
- Transformer Meets Convolution: A Bilateral Awareness Network for Semantic Segmentation of Very Fine Resolution Urban Scene Images
- Length-Adaptive Transformer: Train Once with Length Drop, Use Anytime with Search
- Discriminative Hamiltonian Variational Autoencoder for Accurate Tumor Segmentation in Data-Scarce Regimes
- Towards Biologically Plausible Convolutional Networks
- FPB: Feature Pyramid Branch for Person Re-Identification
- Scatterbrain: Unifying Sparse and Low-rank Attention Approximation
- 3D Object Detection with Pointformer
- Lightning Fast Video Anomaly Detection via Adversarial Knowledge Distillation
- Delving Deep into the Generalization of Vision Transformers under Distribution Shifts
- Asymptotic theory of in-context learning by linear attention
- Augmenting semantic lexicons using word embeddings and transfer learning
- Image-Based Vehicle Classification by Synergizing Features from Supervised and Self-Supervised Learning Paradigms
- Probing Inter-modality: Visual Parsing with Self-Attention for Vision-Language Pre-training
- Dynamic Inference with Neural Interpreters
- Spatial-Temporal Graph Enhanced DETR Towards Multi-Frame 3D Object Detection
- Are queries and keys always relevant? A case study on Transformer wave functions
- Beyond the Frontier: Predicting Unseen Walls from Occupancy Grids by Learning from Floor Plans
- Towards Robust Vision Transformer
- Attention-Enhanced Hybrid Feature Aggregation Network for 3D Brain Tumor Segmentation
- Activation Function Optimization Scheme for Image Classification
- Modularity in Deep Learning: A Survey
- FastLTS: Non-Autoregressive End-to-End Unconstrained Lip-to-Speech Synthesis
- A Tutorial on MRI Reconstruction: From Modern Methods to Clinical Implications
- Rethinking Supervised Pre-training for Better Downstream Transferring
- Generative Art Using Neural Visual Grammars and Dual Encoders
- AI Illustrator: Translating Raw Descriptions into Images by Prompt-based Cross-Modal Generation
- Self-supervised Learning for Clustering of Wireless Spectrum Activity
- Mitigation of Spatial Nonstationarity with Vision Transformers
- Towards Real Zero-Shot Camouflaged Object Segmentation without Camouflaged Annotations
- One4all User Representation for Recommender Systems in E-commerce
- Uni-Perceiver: Pre-training Unified Architecture for Generic Perception for Zero-shot and Few-shot Tasks
- Zero-Shot Pediatric Tuberculosis Detection in Chest X-Rays using Self-Supervised Learning
- A Challenging Benchmark of Anime Style Recognition
- Multimodal Approach for Harmonized System Code Prediction
- Neural Architecture Search using Property Guided Synthesis
- Artificial Intelligence in Drug Discovery: Applications and Techniques
- Learning Robust Correlation with Foundation Model for Weakly-Supervised Few-Shot Segmentation
- Towards Training Stronger Video Vision Transformers for EPIC-KITCHENS-100 Action Recognition
- Number of Attention Heads vs Number of Transformer-Encoders in Computer Vision
- Human Pose Estimation from Ambiguous Pressure Recordings with Spatio-temporal Masked Transformers
- Explainable Enterprise Credit Rating via Deep Feature Crossing Network
- F3-Pruning: A Training-Free and Generalized Pruning Strategy towards Faster and Finer Text-to-Video Synthesis
- Multi-Feature Aggregation in Diffusion Models for Enhanced Face Super-Resolution
- Toward Enhancing Vehicle Color Recognition in Adverse Conditions: A Dataset and Benchmark
- Parameterization of Cross-Token Relations with Relative Positional Encoding for Vision MLP
- BabyNet: Residual Transformer Module for Birth Weight Prediction on Fetal Ultrasound Video
- CAT: Cross-Attention Transformer for One-Shot Object Detection
- Automated Learning Rate Scheduler for Large-batch Training
- Early Detection of Alzheimer's Disease using Bottleneck Transformers
- The Benchmark Lottery
- Distribution-based Emotion Recognition in Conversation
- Learning Vision Transformer with Squeeze and Excitation for Facial Expression Recognition
- DisCo: Remedy Self-supervised Learning on Lightweight Models with Distilled Contrastive Learning
- CycleTransGAN-EVC: A CycleGAN-based Emotional Voice Conversion Model with Transformer
- Do Images really do the Talking? Analysing the significance of Images in Tamil Troll meme classification
- MaIL: A Unified Mask-Image-Language Trimodal Network for Referring Image Segmentation
- Leveraging Angular Distributions for Improved Knowledge Distillation
- Revisiting Medical Image Retrieval via Knowledge Consolidation
- SuperPC: A Single Diffusion Model for Point Cloud Completion, Upsampling, Denoising, and Colorization
- Distilling Missing Modality Knowledge from Ultrasound for Endometriosis Diagnosis with Magnetic Resonance Images
- SwimXYZ: A large-scale dataset of synthetic swimming motions and videos
- Why does my medical AI look at pictures of birds? Exploring the efficacy of transfer learning across domain boundaries
- Evaluation of Generative Models for Emotional 3D Animation Generation in VR
- Efficient Deep Spiking Multi-Layer Perceptrons with Multiplication-Free Inference
- Computing a human-like reaction time metric from stable recurrent vision models
- A General Framework for Generative Self-supervised Learning in Non-invasive Estimation of Physiological Parameters Using Photoplethysmography
- MuraNet: Multi-task Floor Plan Recognition with Relation Attention
- Impact of geolocation data on augmented reality usability: A comparative user test
- Foundation Models for Autonomous Driving Perception: A Survey Through Core Capabilities
- Advances in Medical Image Segmentation: A Comprehensive Survey with a Focus on Lumbar Spine Applications
- Recent Advances in Medical Image Classification
- Robust and Decomposable Average Precision for Image Retrieval
- Comparing Transfer and Meta Learning Approaches on a Unified Few-Shot Classification Benchmark
- Deep Learning and LLM-based Methods Applied to Stellar Lightcurve Classification
- Hepatic vessel segmentation based on 3D swin-transformer with inductive biased multi-head self-attention
- EfficientCLIP: Efficient Cross-Modal Pre-training by Ensemble Confident Learning and Language Modeling
- TransRefer3D: Entity-and-Relation Aware Transformer for Fine-Grained 3D Visual Grounding
- DBIA: Data-free Backdoor Injection Attack against Transformer Networks
- SHAMSUL: Systematic Holistic Analysis to investigate Medical Significance Utilizing Local interpretability methods in deep learning for chest radiography pathology prediction
- EGFE: End-to-end Grouping of Fragmented Elements in UI Designs with Multimodal Learning
- Pose Recognition with Cascade Transformers
- Learning to rumble: Automated elephant call classification, detection and endpointing using deep architectures
- Scalable and Accurate Self-supervised Multimodal Representation Learning without Aligned Video and Text Data
- Video-Text Pre-training with Learned Regions
- CAPE: Encoding Relative Positions with Continuous Augmented Positional Embeddings
- Co-Salient Object Detection with Semantic-Level Consensus Extraction and Dispersion
- Study of positional encoding approaches for Audio Spectrogram Transformers
- Shoulder Implant X-Ray Manufacturer Classification: Exploring with Vision Transformer
- Retinal Malady Classification using AI: A novel ViT-SVM combination architecture
- U-Net with Hierarchical Bottleneck Attention for Landmark Detection in Fundus Images of the Degenerated Retina
- Styleformer: Transformer based Generative Adversarial Networks with Style Vector
- OST: Efficient One-stream Network for 3D Single Object Tracking in Point Clouds
- End-to-End Attention-based Image Captioning
- Should attention be all we need? The epistemic and ethical implications of unification in machine learning
- Pix2Next: Leveraging Vision Foundation Models for RGB to NIR Image Translation
- Pixelated Butterfly: Simple and Efficient Sparse training for Neural Network Models
- SORNet: Spatial Object-Centric Representations for Sequential Manipulation
- AGMB-Transformer: Anatomy-Guided Multi-Branch Transformer Network for Automated Evaluation of Root Canal Therapy
- Deep learning-based identification of precipitation clouds from all-sky camera data for observatory safety
- DAF:re: A Challenging, Crowd-Sourced, Large-Scale, Long-Tailed Dataset For Anime Character Recognition
- Detecting Bone Lesions in X-Ray Under Diverse Acquisition Conditions
- Multimodal Group Emotion Recognition In-the-wild Using Privacy-Compliant Features
- A Federated Learning Benchmark on Tabular Data: Comparing Tree-Based Models and Neural Networks
- Understanding Hyperbolic Metric Learning through Hard Negative Sampling
- SEM-CLIP: Precise Few-Shot Learning for Nanoscale Defect Detection in Scanning Electron Microscope Image
- IDEA: Increasing Text Diversity via Online Multi-Label Recognition for Vision-Language Pre-training
- Towards Generalizable and Robust Face Manipulation Detection via Bag-of-local-feature
- Efficient Image Pre-Training with Siamese Cropped Masked Autoencoders
- Pola4All: survey of polarimetric applications and an open-source toolkit to analyze polarization
- Self supervised learning improves dMMR/MSI detection from histology slides across multiple cancers
- CUPID: Adaptive Curation of Pre-training Data for Video-and-Language Representation Learning
- Towards Attention-based Contrastive Learning for Audio Spoof Detection
- Bringing Attention to CAD: Boundary Representation Learning via Transformer
- A GAN-Enhanced Deep Learning Framework for Rooftop Detection from Historical Aerial Imagery
- gSwin: Gated MLP Vision Model with Hierarchical Structure of Shifted Window
- Self-Supervision, Remote Sensing and Abstraction: Representation Learning Across 3 Million Locations
- Streetscape Analysis with Generative AI (SAGAI): Vision-Language Assessment and Mapping of Urban Scenes
- Reading Between the Lanes: Text VideoQA on the Road
- SATformer: Transformer-Based UNSAT Core Learning
- EDTformer: An Efficient Decoder Transformer for Visual Place Recognition
- Self-supervised Semi-supervised Learning for Data Labeling and Quality Evaluation
- Window-based Channel Attention for Wavelet-enhanced Learned Image Compression
- End-to-End Video Object Detection with Spatial-Temporal Transformers
- Pan-cancer Histopathology WSI Pre-training with Position-aware Masked Autoencoder
- Dark Side Augmentation: Generating Diverse Night Examples for Metric Learning
- SigFormer: Signature Transformers for Deep Hedging
- Automatic Generation of Product-Image Sequence in E-commerce
- Heuristical Comparison of Vision Transformers Against Convolutional Neural Networks for Semantic Segmentation on Remote Sensing Imagery
- Noise-Aware Ensemble Learning for Efficient Radar Modulation Recognition
- ExoTST: Exogenous-Aware Temporal Sequence Transformer for Time Series Prediction
- GN-Transformer: Fusing Sequence and Graph Representation for Improved Code Summarization
- Exploring Deep Learning Methods for Classification of SAR Images: Towards NextGen Convolutions via Transformers
- Recycle-and-Distill: Universal Compression Strategy for Transformer-based Speech SSL Models with Attention Map Reusing and Masking Distillation
- Performance Evaluation of Deep Learning and Transformer Models Using Multimodal Data for Breast Cancer Classification
- CATs: Cost Aggregation Transformers for Visual Correspondence
- Proof Artifact Co-training for Theorem Proving with Language Models
- Efficient Softmax Approximation for Deep Neural Networks with Attention Mechanism
- Monocular Per-Object Distance Estimation with Masked Object Modeling
- Self Attention with Temporal Prior: Can We Learn More from Arrow of Time?
- A Survey of Spatio-Temporal EEG data Analysis: from Models to Applications
- Decentralized Personalization for Federated Medical Image Segmentation via Gossip Contrastive Mutual Learning
- Image-Text Pre-Training for Logo Recognition
- DatUS^2: Data-driven Unsupervised Semantic Segmentation with Pre-trained Self-supervised Vision Transformer
- Attention Approximates Sparse Distributed Memory
- STOA-VLP: Spatial-Temporal Modeling of Object and Action for Video-Language Pre-training
- Rethinking Training from Scratch for Object Detection
- Hire-MLP: Vision MLP via Hierarchical Rearrangement
- How Powerful are Interest Diffusion on Purchasing Prediction: A Case Study of Taocode
- Mamba? Catch The Hype Or Rethink What Really Helps for Image Registration
- The Three Hundred Project: Mapping The Matter Distribution in Galaxy Clusters Via Deep Learning from Multiview Simulated Observations
- Towards Real-Time Monocular Depth Estimation for Robotics: A Survey
- Accurate Patient Alignment without Unnecessary Imaging Dose via Synthesizing Patient-specific 3D CT Images from 2D kV Images
- Tile-Weighted Rate-Distortion Optimized Packet Scheduling for 360 VR Video Streaming
- Self-supervised Video-centralised Transformer for Video Face Clustering
- CrisisViT: A Robust Vision Transformer for Crisis Image Classification
- Automation of Quantum Dot Measurement Analysis via Explainable Machine Learning
- More than Encoder: Introducing Transformer Decoder to Upsample
- Interpreting Vision and Language Generative Models with Semantic Visual Priors
- Camera Adaptation for Fundus-Image-Based CVD Risk Estimation
- Superband: an Electronic-band and Fermi surface structure database of superconductors
- Visual Reasoning: from State to Transformation
- Unsupervised Vision-and-Language Pre-training Without Parallel Images and Captions
- Temporal-Channel Transformer for 3D Lidar-Based Video Object Detection in Autonomous Driving
- Self-Supervised Learning by Estimating Twin Class Distributions
- Semantically Guided Representation Learning For Action Anticipation
- VIDI: A Video Dataset of Incidents
- A Two-part Transformer Network for Controllable Motion Synthesis
- Cross-view Geo-localization with Evolving Transformer
- SHFormer: Dynamic Spectral Filtering Convolutional Neural Network and High-pass Kernel Generation Transformer for Adaptive MRI Reconstruction
- Machine learning with limited data
- How and When Adversarial Robustness Transfers in Knowledge Distillation?
- SCENIC: A JAX Library for Computer Vision Research and Beyond
- Training Deep Neural Networks with Adaptive Momentum Inspired by the Quadratic Optimization
- GroupFormer: Group Activity Recognition with Clustered Spatial-Temporal Transformer
- Multi-Task Self-Training for Learning General Representations
- FMMformer: Efficient and Flexible Transformer via Decomposed Near-field and Far-field Attention
- Solving Machine Learning Problems
- Instance-based Vision Transformer for Subtyping of Papillary Renal Cell Carcinoma in Histopathological Image
- Time-Space Transformers for Video Panoptic Segmentation
- Disentangling Structure and Appearance in ViT Feature Space
- Devil in the Landscapes: Inferring Epidemic Exposure Risks from Street View Imagery
- Harmonizing Feature Attributions Across Deep Learning Architectures: Enhancing Interpretability and Consistency
- BiPC: Bidirectional Probability Calibration for Unsupervised Domain Adaption
- Enabling Efficient Hardware Acceleration of Hybrid Vision Transformer (ViT) Networks at the Edge
- Generalist Models in Medical Image Segmentation: A Survey and Performance Comparison with Task-Specific Approaches
- Emergence of Human-Like Attention in Self-Supervised Vision Transformers: an eye-tracking study
- CASPFormer: Trajectory Prediction from BEV Images with Deformable Attention
- ReCLIP++: Learn to Rectify the Bias of CLIP for Unsupervised Semantic Segmentation
- Efficient onboard multi-task AI architecture based on self-supervised learning
- Deep Implicit Optimization enables Robust Learnable Features for Deformable Image Registration
- Solving the enigma: Enhancing faithfulness and comprehensibility in explanations of deep networks
- ClipFormer: Key-Value Clipping of Transformers on Memristive Crossbars for Write Noise Mitigation
- Transformers with Attentive Federated Aggregation for Time Series Stock Forecasting
- ADF & TransApp: A Transformer-Based Framework for Appliance Detection Using Smart Meter Consumption Series
- Saturn Platform: Foundation Model Operations and Generative AI for Financial Services
- PlaNet-S: Automatic Semantic Segmentation of Placenta
- Deep Representation Learning for Open Vocabulary Electroencephalography-to-Text Decoding
- FocDepthFormer: Transformer with latent LSTM for Depth Estimation from Focal Stack
- VLSlice: Interactive Vision-and-Language Slice Discovery
- CoNeS: Conditional neural fields with shift modulation for multi-sequence MRI translation
- Deep Neural Networks Fused with Textures for Image Classification
- MANER: Multi-Agent Neural Rearrangement Planning of Objects in Cluttered Environments
- SAR ATR under Limited Training Data Via MobileNetV3
- Unsupervised anomaly localization in high-resolution breast scans using deep pluralistic image completion
- Semi-supervised multiscale dual-encoding method for faulty traffic data detection
- LaRa: Latents and Rays for Multi-Camera Bird's-Eye-View Semantic Segmentation
- Are Transformers More Robust? Towards Exact Robustness Verification for Transformers
- An Image Patch is a Wave: Phase-Aware Vision MLP
- Generalized Decision Transformer for Offline Hindsight Information Matching
- No One Representation to Rule Them All: Overlapping Features of Training Methods
- End-to-End Dense Video Grounding via Parallel Regression
- Split and Connect: A Universal Tracklet Booster for Multi-Object Tracking
- Perceptual Image Quality Assessment with Transformers
- Transformer visualization via dictionary learning: contextualized embedding as a linear superposition of transformer factors
- RARTS: An Efficient First-Order Relaxed Architecture Search Method
- GTNet:Guided Transformer Network for Detecting Human-Object Interactions
- Voxel Transformer for 3D Object Detection
- PnP-DETR: Towards Efficient Visual Analysis with Transformers
- ML-EXray: Visibility into ML Deployment on the Edge
- A 7T fMRI dataset of synthetic images for out-of-distribution modeling of vision
- Learning from the few: Fine-grained approach to pediatric wrist pathology recognition on a limited dataset
- Exoplanet Transit Candidate Identification in TESS Full-Frame Images via a Transformer-Based Algorithm
- DyFormer: A Scalable Dynamic Graph Transformer with Provable Benefits on Generalization Ability
- A Computer Vision Approach to Estimate the Localized Sea State
- An Empirical Study of Excitation and Aggregation Design Adaptions in CLIP4Clip for Video-Text Retrieval
- Towards Cardiac MRI Foundation Models: Comprehensive Visual-Tabular Representations for Whole-Heart Assessment and Beyond
- Explainability in AI Based Applications: A Framework for Comparing Different Techniques
- Temporal Query Networks for Fine-grained Video Understanding
- NestQuant: Post-Training Integer-Nesting Quantization for On-Device DNN
- Deblending Overlapping Galaxies in DECaLS Using Transformer-Based Algorithm: A Method Combining Multiple Bands and Data Types
- Analyzing Effects of Mixed Sample Data Augmentation on Model Interpretability
- Vision Transformer for Classification of Breast Ultrasound Images
- Learning from Videos with Deep Convolutional LSTM Networks
- ImageNet-21K Pretraining for the Masses
- Grid Jigsaw Representation with CLIP: A New Perspective on Image Clustering
- ConvNets vs. Transformers: Whose Visual Representations are More Transferable?
- A Simple and Robust Framework for Cross-Modality Medical Image Segmentation applied to Vision Transformers
- Large Language Models and Multimodal Retrieval for Visual Word Sense Disambiguation
- VidTr: Video Transformer Without Convolutions
- A State-of-the-art Survey of Artificial Neural Networks for Whole-slide Image Analysis:from Popular Convolutional Neural Networks to Potential Visual Transformers
- Multimodal Feature Fusion for Video Advertisements Tagging Via Stacking Ensemble
- A Unified Efficient Pyramid Transformer for Semantic Segmentation
- Is Object Detection Necessary for Human-Object Interaction Recognition?
- Two-Stage Adaptive Network for Semi-Supervised Cross-Domain Crater Detection under Varying Scenario Distributions
- COVID-19 Pneumonia Severity Prediction using Hybrid Convolution-Attention Neural Architectures
- MHAttnSurv: Multi-Head Attention for Survival Prediction Using Whole-Slide Pathology Images
- Passive Attention in Artificial Neural Networks Predicts Human Visual Selectivity
- Impact of Ground Truth Quality on Handwriting Recognition
- Beyond Ensemble Averages: Leveraging Climate Model Ensembles for Subseasonal Forecasting
- Drawing Multiple Augmentation Samples Per Image During Training Efficiently Decreases Test Error
- Vis-TOP: Visual Transformer Overlay Processor
- Stochastic Spiking Attention: Accelerating Attention with Stochastic Computing in Spiking Networks
- Spatial-Temporal Transformer for 3D Point Cloud Sequences
- CLIP4Caption ++: Multi-CLIP for Video Caption
- Tiny Models are the Computational Saver for Large Models
- Attention for Image Registration (AiR): an unsupervised Transformer approach
- Quantitative Analysis of Primary Attribution Explainable Artificial Intelligence Methods for Remote Sensing Image Classification
- Quantum optical classifier with superexponential speedup
- Transformer-Enhanced Motion Planner: Attention-Guided Sampling for State-Specific Decision Making
- fruit-SALAD: A Style Aligned Artwork Dataset to reveal similarity perception in image embeddings
- Seg-LSTM: Performance of xLSTM for Semantic Segmentation of Remotely Sensed Images
- KVT: k-NN Attention for Boosting Vision Transformers
- A Spitting Image: Modular Superpixel Tokenization in Vision Transformers
- Delta Keyword Transformer: Bringing Transformers to the Edge through Dynamically Pruned Multi-Head Self-Attention
- MFEViT: A Robust Lightweight Transformer-based Network for Multimodal 2D+3D Facial Expression Recognition
- SPformer: A Transformer Based DRL Decision Making Method for Connected Automated Vehicles
- Explainable Artificial Intelligence for Improved Modeling of Processes
- Locally Enhanced Self-Attention: Combining Self-Attention and Convolution as Local and Context Terms
- Advanced Deep Learning Architectures for Accurate Detection of Subsurface Tile Drainage Pipes from Remote Sensing Images
- Learning to Taste: A Multimodal Wine Dataset
- Exploring vision transformer layer choosing for semantic segmentation
- Toward High Quality Facial Representation Learning
- Induction Network: Audio-Visual Modality Gap-Bridging for Self-Supervised Sound Source Localization
- Pelta: Shielding Transformers to Mitigate Evasion Attacks in Federated Learning
- Multi-temporal crack segmentation in concrete structures using deep learning approaches
- ZRIGF: An Innovative Multimodal Framework for Zero-Resource Image-Grounded Dialogue Generation
- RadioNet: Transformer based Radio Map Prediction Model For Dense Urban Environments
- Self-supervised Model Based on Masked Autoencoders Advance CT Scans Classification
- Go Wider Instead of Deeper
- RTA-Former: Reverse Transformer Attention for Polyp Segmentation
- The impact of memory on learning sequence-to-sequence tasks
- Analyzing and Mitigating Bias for Vulnerable Classes: Towards Balanced Representation in Dataset
- Supervised Representation Learning towards Generalizable Assembly State Recognition
- On convex decision regions in deep network representations
- MvKeTR: Chest CT Report Generation with Multi-View Perception and Knowledge Enhancement
- TransAxx: Efficient Transformers with Approximate Computing
- Fractal Pyramid Networks
- Enhancing Classification with Hierarchical Scalable Query on Fusion Transformer
- Universal Design Methodology for Printable Microstructural Materials via a New Deep Generative Learning Model: Application to a Piezocomposite
- Vision Transformer for Learning Driving Policies in Complex Multi-Agent Environments
- Comparative Analysis of Deep Learning Approaches for Harmful Brain Activity Detection Using EEG
- Integrating Image Features with Convolutional Sequence-to-sequence Network for Multilingual Visual Question Answering
- Trapped in texture bias? A large scale comparison of deep instance segmentation
- Severity Quantification and Lesion Localization of COVID-19 on CXR using Vision Transformer
- Predictive Authoring for Brazilian Portuguese Augmentative and Alternative Communication
- Hierarchical Multi-Label Classification with Missing Information for Benthic Habitat Imagery
- Long-Range Transformer Architectures for Document Understanding
- Reliable Multi-modal Medical Image-to-image Translation Independent of Pixel-wise Aligned Data
- Learning Channel Importance for High Content Imaging with Interpretable Deep Input Channel Mixing
- Sampling Equivariant Self-attention Networks for Object Detection in Aerial Images
- Experimental Standards for Deep Learning in Natural Language Processing Research
- Post-Training Quantization for Vision Transformer
- Transformers as Strong Lens Detectors- From Simulation to Surveys
- DualSwinUnet++: An Enhanced Swin-Unet Architecture With Dual Decoders For PTMC Segmentation
- Weakly-Supervised Temporal Action Localization Through Local-Global Background Modeling
- Downstream-Pretext Domain Knowledge Traceback for Active Learning
- Axial Residual Networks for CycleGAN-based Voice Conversion
- AI as a Tool for Fair Journalism: Case Studies from Malta
- SEVEN: Pruning Transformer Model by Reserving Sentinels
- Compositional Kronecker Context Optimization for Vision-Language Models
- HR-NAS: Searching Efficient High-Resolution Neural Architectures with Lightweight Transformers
- MamT: Multi-view Attention Networks for Mammography Cancer Classification
- Grouped Target Tracking and Seamless People Counting with a 24 GHz MIMO FMCW
- Deep Magnification-Flexible Upsampling over 3D Point Clouds
- Grounding inductive biases in natural images:invariance stems from variations in data
- Deep Insights into Cognitive Decline: A Survey of Leveraging Non-Intrusive Modalities with Deep Learning Techniques
- Joint multi-dimensional dynamic attention and transformer for general image restoration
- Salient Object Ranking with Position-Preserved Attention
- A new rotating machinery fault diagnosis method based on the Time Series Transformer
- SRMF: A Data Augmentation and Multimodal Fusion Approach for Long-Tail UHR Satellite Image Segmentation
- Textual interpretation of transient image classifications from large language models
- Transformed CNNs: recasting pre-trained convolutional layers with self-attention
- Mask6D: Masked Pose Priors For 6D Object Pose Estimation
- PVTAdpNet: Polyp Segmentation using Pyramid vision transformer with a novel Adapter block
- GLiT: Neural Architecture Search for Global and Local Image Transformer
- Transform and Bitstream Domain Image Classification
- Transformer for Polyp Detection
- Weakly-supervised Fingerspelling Recognition in British Sign Language Videos
- A World-Self Model Towards Understanding Intelligence
- A Comparison for Anti-noise Robustness of Deep Learning Classification Methods on a Tiny Object Image Dataset: from Convolutional Neural Network to Visual Transformer and Performer
- A Unified Perspective for Loss-Oriented Imbalanced Learning via Localization
- Tracking Without Re-recognition in Humans and Machines
- On a time-frequency blurring operator with applications in data augmentation
- Assessment of the Reliablity of a Model's Decision by Generalizing Attribution to the Wavelet Domain
- Lightweight Gaze Estimation Model Via Fusion Global Information
- When Medical Imaging Met Self-Attention: A Love Story That Didn't Quite Work Out
- Video Transformer for Deepfake Detection with Incremental Learning
- Guided Context Gating: Learning to leverage salient lesions in retinal fundus images
- Parameter Prediction for Unseen Deep Architectures
- CardioSyntax: end-to-end SYNTAX score prediction -- dataset, benchmark and method
- Subdimensional Expansion Using Attention-Based Learning For Multi-Agent Path Finding
- Contextual Guided Segmentation Framework for Semi-supervised Video Instance Segmentation
- Compare Where It Matters: Using Layer-Wise Regularization To Improve Federated Learning on Heterogeneous Data
- Tsformer: Time series Transformer for tourism demand forecasting
- A Comparison for Patch-level Classification of Deep Learning Methods on Transparent Environmental Microorganism Images: from Convolutional Neural Networks to Visual Transformers
- GasHisSDB: A New Gastric Histopathology Image Dataset for Computer Aided Diagnosis of Gastric Cancer
- Improving ensemble extreme precipitation forecasts using generative artificial intelligence
- Learning Efficient Unsupervised Satellite Image-based Building Damage Detection
- Fluctuation based interpretable analysis scheme for quantum many-body snapshots
- VidLanKD: Improving Language Understanding via Video-Distilled Knowledge Transfer
- Explaining Deep Neural Networks for Bearing Fault Detection with Vibration Concepts
- Scope and Arbitration in Machine Learning Clinical EEG Classification
- Multi-head Ensemble of Smoothed Classifiers for Certified Robustness
- Multi-Scale Feature Fusion using Parallel-Attention Block for COVID-19 Chest X-ray Diagnosis
- Removing Radio Frequency Interference from Auroral Kilometric Radiation with Stacked Autoencoders
- Semantic-guided modeling of spatial relation and object co-occurrence for indoor scene recognition
- Investigating and Improving Latent Density Segmentation Models for Aleatoric Uncertainty Quantification in Medical Imaging
- Dynamic Attention-Guided Diffusion for Image Super-Resolution
- Leveraging Self-Supervised Vision Transformers for Segmentation-based Transfer Function Design
- A Novel Neural Network Training Method for Autonomous Driving Using Semi-Pseudo-Labels and 3D Data Augmentations
- Adaptive Input-image Normalization for Solving the Mode Collapse Problem in GAN-based X-ray Images
- AViTMP: A Tracking-Specific Transformer for Single-Branch Visual Tracking
- Audio-visual child-adult speaker classification in dyadic interactions
- Cognitive Architecture Toward Common Ground Sharing Among Humans and Generative AIs: Trial on Model-Model Interactions in Tangram Naming Task
- Continual Learning: Forget-free Winning Subnetworks for Video Representations
- Transformers in Unsupervised Structure-from-Motion
- Analysis of the Two-Step Heterogeneous Transfer Learning for Laryngeal Blood Vessel Classification: Issue and Improvement
- Enhancing Cross-Modal Contextual Congruence for Crowdfunding Success using Knowledge-infused Learning
- Visual Reasoning in Object-Centric Deep Neural Networks: A Comparative Cognition Approach
- Transfer Learning with Pre-trained Conditional Generative Models
- Reply with Sticker: New Dataset and Model for Sticker Retrieval
- TSCM: A Teacher-Student Model for Vision Place Recognition Using Cross-Metric Knowledge Distillation
- FashionFail: Addressing Failure Cases in Fashion Object Detection and Segmentation
- KWT-Tiny: RISC-V Accelerated, Embedded Keyword Spotting Transformer
- Don't Fear Peculiar Activation Functions: EUAF and Beyond
- SOOD-ImageNet: a Large-Scale Dataset for Semantic Out-Of-Distribution Image Classification and Semantic Segmentation
- MAX: Masked Autoencoder for X-ray Fluorescence in Geological Investigation
- Automated neuroradiological support systems for multiple cerebrovascular disease markers -- A systematic review and meta-analysis
- Mixture-of-Experts Graph Transformers for Interpretable Particle Collision Detection
- GLoG-CSUnet: Enhancing Vision Transformers with Adaptable Radiomic Features for Medical Image Segmentation
- Cutting-edge 3D reconstruction solutions for underwater coral reef images: A review and comparison
- Bayesian SegNet for Semantic Segmentation with Improved Interpretation of Microstructural Evolution During Irradiation of Materials
- Benchmarking Deep Learning Methods for Irradiance Estimation from Sky Images with Applications to Video Prediction-Based Irradiance Nowcasting
- ISP-AD: A Large-Scale Real-World Dataset for Advancing Industrial Anomaly Detection with Synthetic and Real Defects
- Completing Spatial Transcriptomics Data for Gene Expression Prediction Benchmarking
- Benchmarking histopathology foundation models in a multi-center dataset for skin cancer subtyping
- Efficient Video Transformers with Spatial-Temporal Token Selection
- CLIP-RL: Surgical Scene Segmentation Using Contrastive Language-Vision Pretraining & Reinforcement Learning
- Towards Practical Deployment-Stage Backdoor Attack on Deep Neural Networks
- Model Interpretability and Rationale Extraction by Input Mask Optimization
- Dual Interaction Network with Cross-Image Attention for Medical Image Segmentation
- Enhancing Rotated Object Detection via Anisotropic Gaussian Bounding Box and Bhattacharyya Distance
- Learning Efficient Multi-Agent Cooperative Visual Exploration
- Transport-Related Surface Detection with Machine Learning: Analyzing Temporal Trends in Madrid and Vienna
- The Application of Deep Learning for Lymph Node Segmentation: A Systematic Review
- Visual hallucination detection in large vision-language models via evidential conflict
- CAE-Transformer: Transformer-based Model to Predict Invasiveness of Lung Adenocarcinoma Subsolid Nodules from Non-thin Section 3D CT Scans
- Deep Feature Response Discriminative Calibration
- Score-Based Generative Classifiers
- DREAM: Domain-agnostic Reverse Engineering Attributes of Black-box Model
- An object detection approach for lane change and overtake detection from motion profiles
- Clarifying Myths About the Relationship Between Shape Bias, Accuracy, and Robustness
- Convolutional Transformer-Based Image Compression
- SAttention: Improving Long Sequence Attention with Smoothed Skeleton Sketching
- Flexible Communication for Optimal Distributed Learning over Unpredictable Networks
- TDViT: Temporal Dilated Video Transformer for Dense Video Tasks
- Sparse Double Descent in Vision Transformers: real or phantom threat?
- HartleyMHA: Self-Attention in Frequency Domain for Resolution-Robust and Parameter-Efficient 3D Image Segmentation
- EWasteNet: A Two-Stream Data Efficient Image Transformer Approach for E-Waste Classification
- Advancing Post Hoc Case Based Explanation with Feature Highlighting
- On Masked Pre-training and the Marginal Likelihood
- UniNet: Unified Architecture Search with Convolution, Transformer, and MLP
- VideoLightFormer: Lightweight Action Recognition using Transformers
- Concurrent Neural Tree and Data Preprocessing AutoML for Image Classification
- Spectral Unsupervised Domain Adaptation for Visual Recognition
- Long-Short Temporal Contrastive Learning of Video Transformers
- NeuraCrypt: Hiding Private Health Data via Random Neural Networks for Public Training
- TED-net: Convolution-free T2T Vision Transformer-based Encoder-decoder Dilation network for Low-dose CT Denoising
- Semi-Supervised 3D Hand-Object Poses Estimation with Interactions in Time
- GroupBERT: Enhanced Transformer Architecture with Efficient Grouped Structures
- A Stronger Baseline for Ego-Centric Action Detection
- Co-advise: Cross Inductive Bias Distillation
- I2C2W: Image-to-Character-to-Word Transformers for Accurate Scene Text Recognition
- Vehicle Re-identification Method Based on Vehicle Attribute and Mutual Exclusion Between Cameras
- EEG-ConvTransformer for Single-Trial EEG based Visual Stimuli Classification
- RAMS-Trans: Recurrent Attention Multi-scale Transformer forFine-grained Image Recognition
- Domain-Adversarial Training of Self-Attention Based Networks for Land Cover Classification using Multi-temporal Sentinel-2 Satellite Imagery
- Armour: Generalizable Compact Self-Attention for Vision Transformers
- Causal Attention for Unbiased Visual Recognition
- Audio-Visual Transformer Based Crowd Counting
- 3D Human Texture Estimation from a Single Image with Transformers
- TEASEL: A Transformer-Based Speech-Prefixed Language Model
- TS-CAM: Token Semantic Coupled Attention Map for Weakly Supervised Object Localization
- Alignment Attention by Matching Key and Query Distributions
- Large Scale Neural Architecture Search with Polyharmonic Splines
- Self-supervised pseudo-colorizing of masked cells
- MuG: A Multimodal Classification Benchmark on Game Data with Tabular, Textual, and Visual Fields
- SWIFT: Expedited Failure Recovery for Large-scale DNN Training
- GenCeption: Evaluate Vision LLMs with Unlabeled Unimodal Data
- Radio Halo Detection in MWA Data using Deep Neural Networks and Generative Data Augmentation
- Knee or ROC
- Augmented Shortcuts for Vision Transformers
- Harnessing Orthogonality to Train Low-Rank Neural Networks
- Enhance Diffusion to Improve Robust Generalization
- Enhancing Transformer for Video Understanding Using Gated Multi-Level Attention and Temporal Adversarial Training
- Probabilistic Attention for Interactive Segmentation
- Video-based Person Re-identification without Bells and Whistles
- Multi-Stream Attention Learning for Monocular Vehicle Velocity and Inter-Vehicle Distance Estimation
- On the robustness of self-supervised representations for multi-view object classification
- Learning Transformer Features for Image Quality Assessment
- A Relational Model for One-Shot Classification
- ViGEO: an Assessment of Vision GNNs in Earth Observation
- Google Landmark Retrieval 2021 Competition Third Place Solution
- Interpreting A Pre-trained Model Is A Key For Model Architecture Optimization: A Case Study On Wav2Vec 2.0
- Attend to Who You Are: Supervising Self-Attention for Keypoint Detection and Instance-Aware Association
- HAISTA-NET: Human Assisted Instance Segmentation Through Attention
- Improving White-box Robustness of Pre-processing Defenses via Joint Adversarial Training
- Point Cloud Learning with Transformer
- Composable Generative Models
- Designing Pre-training Datasets from Unlabeled Data for EEG Classification with Transformers
- Exceeding the Limits of Visual-Linguistic Multi-Task Learning
- Adversarial AutoMixup
- Multi-modal Residual Perceptron Network for Audio-Video Emotion Recognition
- Group-based Distinctive Image Captioning with Memory Attention
- Relating Blindsight and AI: A Review
- Depth Infused Binaural Audio Generation using Hierarchical Cross-Modal Attention
- Hybrid Focal and Full-Range Attention Based Graph Transformers
- Tuning-less Object Naming with a Foundation Model
- torchdistill Meets Hugging Face Libraries for Reproducible, Coding-Free Deep Learning Studies: A Case Study on NLP
- 3D High-Fidelity Mask Face Presentation Attack Detection Challenge
- Soften the Mask: Adaptive Temporal Soft Mask for Efficient Dynamic Facial Expression Recognition
- Image Augmentation with Controlled Diffusion for Weakly-Supervised Semantic Segmentation
- Combating Label Noise With A General Surrogate Model For Sample Selection
- Human Activity Recognition in an Open World
- Guiding Query Position and Performing Similar Attention for Transformer-Based Detection Heads
- Deep learning reveals key predictors of thermal conductivity in covalent organic frameworks
- Semantic Segmentation on VSPW Dataset through Aggregation of Transformer Models
- Deep set conditioned latent representations for action recognition
- Hierarchical Attention-based Age Estimation and Bias Estimation
- TRIGS: Trojan Identification from Gradient-based Signatures
- What Matters for Ad-hoc Video Search? A Large-scale Evaluation on TRECVID
- A novel framework employing deep multi-attention channels network for the autonomous detection of metastasizing cells through fluorescence microscopy
- Energy Attack: On Transferring Adversarial Examples
- Framework-agnostic Semantically-aware Global Reasoning for Segmentation
- CT-block: a novel local and global features extractor for point cloud
- Understanding the predication mechanism of deep learning through error propagation among parameters in strong lensing case
- Benchmarking Deep Learning Models for Raman Spectroscopy Across Open-Source Datasets
- A Survey of Large-Scale Deep Learning Serving System Optimization: Challenges and Opportunities
- An Empirical Study of Vehicle Re-Identification on the AI City Challenge
- Evaluating Graphical Perception Capabilities of Vision Transformers
- Cascaded Head-colliding Attention
- Beyond Individual Input for Deep Anomaly Detection on Tabular Data
- Estimating the Robustness of Classification Models by the Structure of the Learned Feature-Space
- Revamping Cross-Modal Recipe Retrieval with Hierarchical Transformers and Self-supervised Learning
- Classification of COVID-19 cases from chest CT volumes using hybrid model of 3D CNN and 3D MLP-Mixer
- printf: Preference Modeling Based on User Reviews with Item Images and Textual Information via Graph Learning
- MammoMix: Leveraging Mixture of Experts for Robust Mammogram Breast Detection
- The Image Local Autoregressive Transformer
- Precision at Scale: Domain-Specific Datasets On-Demand
- Automatic Quality Assessment of First Trimester Crown-Rump-Length Ultrasound Images
- IgCONDA-PET: Weakly-Supervised PET Anomaly Detection using Implicitly-Guided Attention-Conditional Counterfactual Diffusion Modeling -- a Multi-Center, Multi-Cancer, and Multi-Tracer Study
- On Spectral Properties of Gradient-based Explanation Methods
- Overview of Tencent Multi-modal Ads Video Understanding Challenge
- When Better Eyes Lead to Blindness: A Diagnostic Study of the Information Bottleneck in CNN-LSTM Image Captioning Models
- SFB-net for cardiac segmentation: Bridging the semantic gap with attention
- Image Captions are Natural Prompts for Text-to-Image Models
- PSF-based Analysis for Detecting Unresolved Wide Binaries
- ComFace: Facial Representation Learning with Synthetic Data for Comparing Faces
- Towards Early Prediction of Human iPSC Reprogramming Success
- PointMixer: MLP-Mixer for Point Cloud Understanding
- Thought Flow Nets: From Single Predictions to Trains of Model Thought
- Transformer Assisted Convolutional Network for Cell Instance Segmentation
- Local Patch AutoAugment with Multi-Agent Collaboration
- Fast Fishing: Approximating BAIT for Efficient and Scalable Deep Active Image Classification
- ViTAS: Vision Transformer Architecture Search
- vieCap4H-VLSP 2021: Vietnamese Image Captioning for Healthcare Domain using Swin Transformer and Attention-based LSTM
- Swapped Logit Distillation via Bi-level Teacher Alignment
- Multimodal Transformer with Variable-length Memory for Vision-and-Language Navigation
- Disentanglement of Latent Representations via Causal Interventions
- Semi-Supervised Vision Transformers
- Self-Distilled Self-Supervised Representation Learning
- Trivial or impossible -- dichotomous data difficulty masks model differences (on ImageNet and beyond)
- Modular Adaptation for Cross-Domain Few-Shot Learning
- Adaptive Discriminative Regularization for Visual Classification
- Addressing Weak Decision Boundaries in Image Classification by Leveraging Web Search and Generative Models
- PairConnect: A Compute-Efficient MLP Alternative to Attention
- Unsupervised Salient Patch Selection for Data-Efficient Reinforcement Learning
- U-R-VEDA: Integrating UNET, Residual Links, Edge and Dual Attention, and Vision Transformer for Accurate Semantic Segmentation of CMRs
- Compositional Attention: Disentangling Search and Retrieval
- Shuffle Transformer with Feature Alignment for Video Face Parsing
- Improving Token-based Object Detection with Video
- Generative Iris Prior Embedded Transformer for Iris Restoration
- Benchmarking Feature Extractors for Reinforcement Learning-Based Semiconductor Defect Localization
- Make an Omelette with Breaking Eggs: Zero-Shot Learning for Novel Attribute Synthesis
- VTAMIQ: Transformers for Attention Modulated Image Quality Assessment
- Deep Learning Methods for Detecting Thermal Runaway Events in Battery Production Lines
- OadTR: Online Action Detection with Transformers
- Data-Efficient Language-Supervised Zero-Shot Learning with Self-Distillation
- Feed-Forward Optimization With Delayed Feedback for Neural Network Training
- Design of Macroscale Optical Systems with Metaoptics Using Transformer-Based Neural Networks
- Convolutional Gated MLP: Combining Convolutions & gMLP
- FoveaTer: Foveated Transformer for Image Classification
- Dilated Convolution with Learnable Spacings: beyond bilinear interpolation
- Fast Line Search for Multi-Task Learning
- The Goofus & Gallant Story Corpus for Practical Value Alignment
- Transformer-based Dual Relation Graph for Multi-label Image Recognition
- TraVLR: Now You See It, Now You Don't! A Bimodal Dataset for Evaluating Visio-Linguistic Reasoning
- Hybrid BYOL-ViT: Efficient approach to deal with small datasets
- Audiomer: A Convolutional Transformer For Keyword Spotting
- Contrastive Forward-Forward: A Training Algorithm of Vision Transformer
- Wildlife Product Trading in Online Social Networks: A Case Study on Ivory-Related Product Sales Promotion Posts
- Teaching Autoregressive Language Models Complex Tasks By Demonstration
- Image-Like Graph Representations for Improved Molecular Property Prediction
- Motion Consistency Loss for Monocular Visual Odometry with Attention-Based Deep Learning
- CLIP4Caption: CLIP for Video Caption
- Global Interaction Modelling in Vision Transformer via Super Tokens
- Improved Drug-target Interaction Prediction with Intermolecular Graph Transformer
- Improving FHB Screening in Wheat Breeding Using an Efficient Transformer Model
- NoFADE: Analyzing Diminishing Returns on CO2 Investment
- MC-SSL0.0: Towards Multi-Concept Self-Supervised Learning
- ViFiT: Reconstructing Vision Trajectories from IMU and Wi-Fi Fine Time Measurements
- Pathologies in priors and inference for Bayesian transformers
- UBoCo : Unsupervised Boundary Contrastive Learning for Generic Event Boundary Detection
- BERMo: What can BERT learn from ELMo?
- Masked Autoencoders with Multi-Window Local-Global Attention Are Better Audio Learners
- KST-Mixer: Kinematic Spatio-Temporal Data Mixer For Colon Shape Estimation
- On Inductive Biases for Machine Learning in Data Constrained Settings
- An implementation of the "Guess who?" game using CLIP
- Can we Trust Chatbots for now? Accuracy, reproducibility, traceability; a Case Study on Leonardo da Vinci's Contribution to Astronomy
- SpaceEdit: Learning a Unified Editing Space for Open-Domain Image Editing
- A SAM based Tool for Semi-Automatic Food Annotation
- Portmanteauing Features for Scene Text Recognition
- Exploration into Translation-Equivariant Image Quantization
- Aligned Divergent Pathways for Omni-Domain Generalized Person Re-Identification
- 3rd Place Solution for NeurIPS 2021 Shifts Challenge: Vehicle Motion Prediction
- Synthesizing Photorealistic Images with Deep Generative Learning
- DARES: Depth Anything in Robotic Endoscopic Surgery with Self-supervised Vector-LoRA of the Foundation Model
- SwinSF: Image Reconstruction from Spatial-Temporal Spike Streams
- Can't Fool Me: Adversarially Robust Transformer for Video Understanding
- ScrewSense: Mapping the Invisible - Anomaly Detection and Error Classification in Screwdriving Processes
- CvS: Classification via Segmentation For Small Datasets
- PatchGame: Learning to Signal Mid-level Patches in Referential Games
- Knowledge graphs for empirical concept retrieval
- Low-Rank+Sparse Tensor Compression for Neural Networks
- AdaGlimpse: Active Visual Exploration with Arbitrary Glimpse Position and Scale
- ViT-Inception-GAN for Image Colourising
- ProSTformer: Pre-trained Progressive Space-Time Self-attention Model for Traffic Flow Forecasting
- T-EMDE: Sketching-based global similarity for cross-modal retrieval
- All You Can Embed: Natural Language based Vehicle Retrieval with Spatio-Temporal Transformers
- HindSight: A Graph-Based Vision Model Architecture For Representing Part-Whole Hierarchies
- DiffAugment: Diffusion based Long-Tailed Visual Relationship Recognition
- Attention-based Neural Network for Driving Environment Complexity Perception
- NL-FCOS: Improving FCOS through Non-Local Modules for Object Detection
- PARMESAN: Parameter-Free Memory Search and Transduction for Dense Prediction Tasks
- Shape registration in the time of transformers
- Adjustable Robust Transformer for High Myopia Screening in Optical Coherence Tomography
- Case Relation Transformer: A Crossmodal Language Generation Model for Fetching Instructions
- NP-DRAW: A Non-Parametric Structured Latent Variable Model for Image Generation
- SERE: Exploring Feature Self-relation for Self-supervised Transformer
- Solving morphological analogies: from retrieval to generation
- Knowledge Transfer by Discriminative Pre-training for Academic Performance Prediction
- Synthetic Generation of Three-Dimensional Cancer Cell Models from Histopathological Images
- Weighted Ensemble Models Are Strong Continual Learners
- VQ-HPS: Human Pose and Shape Estimation in a Vector-Quantized Latent Space
- Class-Incremental Domain Adaptation with Smoothing and Calibration for Surgical Report Generation
- Collaborating Foundation Models for Domain Generalized Semantic Segmentation
- A Probabilistic Method to Predict Classifier Accuracy on Larger Datasets given Small Pilot Data
- VidStyleODE: Disentangled Video Editing via StyleGAN and NeuralODEs
- Parameter-efficient Multi-Task and Multi-Domain Learning using Factorized Tensor Networks
- Three Pillars improving Vision Foundation Model Distillation for Lidar
- Context Normalization Layer with Applications
- Vision and Structured-Language Pretraining for Cross-Modal Food Retrieval
- Refine Neutrino Events Reconstruction with BEiT-3
- Bayesian Attention Networks for Data Compression
- Exploitation of Hidden Context in Dynamic Movement Forecasting: A Neural Network Journey from Recurrent to Graph Neural Networks and General Purpose Transformers
- Localized Conformal Prediction for Image Classification with Vision-Language Models
- The Emerging Paradigm of Geospatial Foundation Models: From Pre-Training to Agentic Reasoning
- Implementation of transformer-based LLMs with large-scale optoelectronic neurons on a CMOS compatible platform
- Collaborative Filtering Through Weighted Similarities of User and Item Embeddings
- Is Complete Labeling Necessary? Understanding Active Learning in Longitudinal Medical Imaging
- RTGMFF: Enhanced fMRI-based Brain Disorder Diagnosis via ROI-driven Text Generation and Multimodal Feature Fusion
- Skeletonization-Based Adversarial Perturbations on Large Vision Language Model's Mathematical Text Recognition
- Efficient Pyramidal Analysis of Gigapixel Images on a Decentralized Modest Computer Cluster
- OCELOT 2023: Cell Detection from Cell-Tissue Interaction Challenge
- Diff-3DCap: Shape Captioning with Diffusion Models
- Calibrated Self-supervised Vision Transformers Improve Intracranial Arterial Calcification Segmentation from Clinical CT Head Scans
- Homography augumented momentum constrastive learning for SAR image retrieval
- Weakly-Supervised Monocular Depth Estimationwith Resolution-Mismatched Data
- Hydra: A System for Large Multi-Model Deep Learning
- Deep Classifiers with Label Noise Modeling and Distance Awareness
- Spline-based Transformers
- Ripple Attention for Visual Perception with Sub-quadratic Complexity
- Attention-Free Keyword Spotting
- Enhancing Multi-Exposure High Dynamic Range Imaging with Overlapped Codebook for Improved Representation Learning
- The Efficiency Misnomer
- Applying supervised and reinforcement learning methods to create neural-network-based agents for playing StarCraft II
- Galaxy Morphological Classification with Efficient Vision Transformer
- Saliency strikes back: How filtering out high frequencies improves white-box explanations
- Topological Regularization for Dense Prediction
- Spatially Constrained Transformer with Efficient Global Relation Modelling for Spatio-Temporal Prediction