Going Deeper with Convolutions

Abstract

We propose a deep convolutional neural network architecture codenamed "Inception", which was responsible for setting the new state of the art for classification and detection in the ImageNet Large-Scale Visual Recognition Challenge 2014 (ILSVRC 2014). The main hallmark of this architecture is the improved utilization of the computing resources inside the network. This was achieved by a carefully crafted design that allows for increasing the depth and width of the network while keeping the computational budget constant. To optimize quality, the architectural decisions were based on the Hebbian principle and the intuition of multi-scale processing. One particular incarnation used in our submission for ILSVRC 2014 is called GoogLeNet, a 22 layers deep network, the quality of which is assessed in the context of classification and detection.

References in corpus (2)

• DeepPose: Human Pose Estimation via Deep Neural Networks
• OverFeat: Integrated Recognition, Localization and Detection using Convolutional Networks

Cited by in corpus (589)

• Very Deep Convolutional Networks for Large-Scale Image Recognition
• Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift
• A Survey on Deep Learning in Medical Image Analysis
• MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications
• Conditional Generative Adversarial Nets
• TensorFlow: A system for large-scale machine learning
• Explaining and Harnessing Adversarial Examples
• Semantic Image Segmentation with Deep Convolutional Nets and Fully Connected CRFs
• Deep Compression: Compressing Deep Neural Networks with Pruning, Trained Quantization and Huffman Coding
• Convolutional Neural Networks for Medical Image Analysis: Full Training or Fine Tuning?
• Axiomatic Attribution for Deep Networks
• Striving for Simplicity: The All Convolutional Net
• Attention Mechanisms in Computer Vision: A Survey
• Recurrent Neural Network Regularization
• Empirical Evaluation of Rectified Activations in Convolutional Network
• Deep Speech 2: End-to-End Speech Recognition in English and Mandarin
• Binarized Neural Networks: Training Deep Neural Networks with Weights and Activations Constrained to +1 or -1
• FitNets: Hints for Thin Deep Nets
• Conditional Image Synthesis With Auxiliary Classifier GANs
• Densely Connected Convolutional Networks
• BinaryConnect: Training Deep Neural Networks with binary weights during propagations
• Learning Face Representation from Scratch
• End-to-End Training of Deep Visuomotor Policies
• LSUN: Construction of a Large-scale Image Dataset using Deep Learning with Humans in the Loop
• Action Recognition with Trajectory-Pooled Deep-Convolutional Descriptors
• Going Deeper in Facial Expression Recognition using Deep Neural Networks
• ParseNet: Looking Wider to See Better
• cuDNN: Efficient Primitives for Deep Learning
• Compressing Deep Convolutional Networks using Vector Quantization
• An Analysis of Deep Neural Network Models for Practical Applications
• Simultaneous Feature Learning and Hash Coding with Deep Neural Networks
• Towards Better Exploiting Convolutional Neural Networks for Remote Sensing Scene Classification
• Data-Efficient Image Recognition with Contrastive Predictive Coding
• DeepID3: Face Recognition with Very Deep Neural Networks
• ShuffleNet: An Extremely Efficient Convolutional Neural Network for Mobile Devices
• Fully Convolutional Networks for Semantic Segmentation
• Network Trimming: A Data-Driven Neuron Pruning Approach towards Efficient Deep Architectures
• AutoAugment: Learning Augmentation Policies from Data
• Learning both Weights and Connections for Efficient Neural Networks
• Towards Deep Neural Network Architectures Robust to Adversarial Examples
• Learning Deconvolution Network for Semantic Segmentation
• Bayesian Convolutional Neural Networks with Bernoulli Approximate Variational Inference
• Fixed Point Quantization of Deep Convolutional Networks
• Training Deep Neural Networks on Noisy Labels with Bootstrapping
• AtomNet: A Deep Convolutional Neural Network for Bioactivity Prediction in Structure-based Drug Discovery
• FPGA-based Accelerators of Deep Learning Networks for Learning and Classification: A Review
• Deep Representation Learning with Part Loss for Person Re-Identification
• Learning Structured Sparsity in Deep Neural Networks
• Classifying and Segmenting Microscopy Images Using Convolutional Multiple Instance Learning
• DenseBox: Unifying Landmark Localization with End to End Object Detection
• Action-Conditional Video Prediction using Deep Networks in Atari Games
• YOLO9000: Better, Faster, Stronger
• PlaNet - Photo Geolocation with Convolutional Neural Networks
• Deep Predictive Coding Networks for Video Prediction and Unsupervised Learning
• SphereFace: Deep Hypersphere Embedding for Face Recognition
• An Empirical Evaluation of Deep Learning on Highway Driving
• Massively Multitask Networks for Drug Discovery
• Massively Parallel Methods for Deep Reinforcement Learning
• Towards Good Practices for Very Deep Two-Stream ConvNets
• Convolutional neural networks with low-rank regularization
• Channel Pruning for Accelerating Very Deep Neural Networks
• Fractional Max-Pooling
• CBAM: Convolutional Block Attention Module
• Residual Attention Network for Image Classification
• Pyramid Scene Parsing Network
• Aligning Books and Movies: Towards Story-like Visual Explanations by Watching Movies and Reading Books
• FusionNet: A deep fully residual convolutional neural network for image segmentation in connectomics
• Convolutional Pose Machines
• Simple Baseline for Visual Question Answering
• Multi-view Convolutional Neural Networks for 3D Shape Recognition
• Deep Learning Enables Automatic Detection and Segmentation of Brain Metastases on Multi-Sequence MRI
• Beyond Short Snippets: Deep Networks for Video Classification
• Learning Spatio-Temporal Representation with Pseudo-3D Residual Networks
• Are You Talking to a Machine? Dataset and Methods for Multilingual Image Question Answering
• A Convolutional Neural Network Neutrino Event Classifier
• Image Captioning with Semantic Attention
• ReNet: A Recurrent Neural Network Based Alternative to Convolutional Networks
• Deep Gaze I: Boosting Saliency Prediction with Feature Maps Trained on ImageNet
• Improving Object Detection with Deep Convolutional Networks via Bayesian Optimization and Structured Prediction
• An empirical study on evaluation metrics of generative adversarial networks
• Flattened Convolutional Neural Networks for Feedforward Acceleration
• CNN-RNN: A Unified Framework for Multi-label Image Classification
• Learning Deep Features for Discriminative Localization
• Provable approximation properties for deep neural networks
• All you need is a good init
• Effective Use of Word Order for Text Categorization with Convolutional Neural Networks
• EDA: Easy Data Augmentation Techniques for Boosting Performance on Text Classification Tasks
• Sequence to Sequence -- Video to Text
• Harmonious Attention Network for Person Re-Identification
• WRPN: Wide Reduced-Precision Networks
• Dilated Residual Networks
• FusionNet: 3D Object Classification Using Multiple Data Representations
• Training Deeper Convolutional Networks with Deep Supervision
• A Neural Autoregressive Approach to Collaborative Filtering
• Multifaceted Feature Visualization: Uncovering the Different Types of Features Learned By Each Neuron in Deep Neural Networks
• Less-forgetting Learning in Deep Neural Networks
• Visual Entailment: A Novel Task for Fine-Grained Image Understanding
• Galaxy Zoo: Probabilistic Morphology through Bayesian CNNs and Active Learning
• A Joint Convolutional Neural Networks and Context Transfer for Street Scenes Labeling
• Net2Net: Accelerating Learning via Knowledge Transfer
• Fully automatic detection and segmentation of abdominal aortic thrombus in post-operative CTA images using deep convolutional neural networks
• VideoBERT: A Joint Model for Video and Language Representation Learning
• Deep Visual-Semantic Alignments for Generating Image Descriptions
• An Entropy-based Pruning Method for CNN Compression
• Delving Deeper into Convolutional Networks for Learning Video Representations
• Beyond Data and Model Parallelism for Deep Neural Networks
• Discovering Hidden Factors of Variation in Deep Networks
• Good Practice in CNN Feature Transfer
• Memory Bounded Deep Convolutional Networks
• Predicting Depth, Surface Normals and Semantic Labels with a Common Multi-Scale Convolutional Architecture
• SVDNet for Pedestrian Retrieval
• Learning Contextual Dependencies with Convolutional Hierarchical Recurrent Neural Networks
• Fully Convolutional Neural Networks for Crowd Segmentation
• Swapout: Learning an ensemble of deep architectures
• GeoNet: Unsupervised Learning of Dense Depth, Optical Flow and Camera Pose
• Semantic Autoencoder for Zero-Shot Learning
• Attention for Fine-Grained Categorization
• Person Transfer GAN to Bridge Domain Gap for Person Re-Identification
• Chemception: A Deep Neural Network with Minimal Chemistry Knowledge Matches the Performance of Expert-developed QSAR/QSPR Models
• Evaluating Two-Stream CNN for Video Classification
• Generalizing Pooling Functions in Convolutional Neural Networks: Mixed, Gated, and Tree
• The Importance of Skip Connections in Biomedical Image Segmentation
• Human Action Recognition using Factorized Spatio-Temporal Convolutional Networks
• Convolutional Neural Networks Applied to Neutrino Events in a Liquid Argon Time Projection Chamber
• APAC: Augmented PAttern Classification with Neural Networks
• Scale-Invariant Convolutional Neural Networks
• Flow-Guided Feature Aggregation for Video Object Detection
• ThiNet: A Filter Level Pruning Method for Deep Neural Network Compression
• What Do We Understand About Convolutional Networks?
• Switching Convolutional Neural Network for Crowd Counting
• Discovering New Strong Gravitational Lenses in the DESI Legacy Imaging Surveys
• Learning Deep Feature Representations with Domain Guided Dropout for Person Re-identification
• Super Mario as a String: Platformer Level Generation Via LSTMs
• CondenseNet: An Efficient DenseNet using Learned Group Convolutions
• DSOD: Learning Deeply Supervised Object Detectors from Scratch
• LittleYOLO-SPP: A Delicate Real-Time Vehicle Detection Algorithm
• Universal adversarial perturbations
• Towards Interpretable Deep Neural Networks by Leveraging Adversarial Examples
• Classification of red blood cell shapes in flow using outlier tolerant machine learning
• Improving the Robustness of Deep Neural Networks via Stability Training
• DeepStereo: Learning to Predict New Views from the World's Imagery
• Measuring the Algorithmic Efficiency of Neural Networks
• Exploiting Local Features from Deep Networks for Image Retrieval
• Peephole: Predicting Network Performance Before Training
• Reduced-Precision Strategies for Bounded Memory in Deep Neural Nets
• Fisher Vectors Derived from Hybrid Gaussian-Laplacian Mixture Models for Image Annotation
• Neural Activation Constellations: Unsupervised Part Model Discovery with Convolutional Networks
• DenseCap: Fully Convolutional Localization Networks for Dense Captioning
• ME R-CNN: Multi-Expert R-CNN for Object Detection
• Facial Expression Recognition from World Wild Web
• Deep Neural Networks are Easily Fooled: High Confidence Predictions for Unrecognizable Images
• Applying deep learning to classify pornographic images and videos
• Exploiting Image-trained CNN Architectures for Unconstrained Video Classification
• Learning Spatio-Temporal Features with 3D Residual Networks for Action Recognition
• A Novel Multi-task Deep Learning Model for Skin Lesion Segmentation and Classification
• DeepID-Net: Deformable Deep Convolutional Neural Networks for Object Detection
• GossipGraD: Scalable Deep Learning using Gossip Communication based Asynchronous Gradient Descent
• Learning Physical Intuition of Block Towers by Example
• Adversarial Complementary Learning for Weakly Supervised Object Localization
• Convolutional Clustering for Unsupervised Learning
• Dynamic Few-Shot Visual Learning without Forgetting
• Illuminating Pedestrians via Simultaneous Detection & Segmentation
• Webly Supervised Learning of Convolutional Networks
• Background rejection in NEXT using deep neural networks
• Bilinear CNNs for Fine-grained Visual Recognition
• Effective Quantization Methods for Recurrent Neural Networks
• A Real-time Hand Gesture Recognition and Human-Computer Interaction System
• Latent Embeddings for Zero-shot Classification
• A Probabilistic Theory of Deep Learning
• Deep Reinforcement Learning-based Image Captioning with Embedding Reward
• Training Skinny Deep Neural Networks with Iterative Hard Thresholding Methods
• Cognitive Psychology for Deep Neural Networks: A Shape Bias Case Study
• Learning Feature Pyramids for Human Pose Estimation
• DeepLogo: Hitting Logo Recognition with the Deep Neural Network Hammer
• Action Recognition with Image Based CNN Features
• Detecting and Recognizing Human-Object Interactions
• FRnet-DTI: Deep Convolutional Neural Networks with Evolutionary and Structural Features for Drug-Target Interaction
• Structured Probabilistic Pruning for Convolutional Neural Network Acceleration
• Multimodal Convolutional Neural Networks for Matching Image and Sentence
• Deep Transfer Learning for Star Cluster Classification: I. Application to the PHANGS-HST Survey
• DASH: Deep Learning for the Automated Spectral Classification of Supernovae and their Hosts
• Learning Spatial Regularization with Image-level Supervisions for Multi-label Image Classification
• Trained Quantization Thresholds for Accurate and Efficient Fixed-Point Inference of Deep Neural Networks
• Learning by Association - A versatile semi-supervised training method for neural networks
• Driving Scene Perception Network: Real-time Joint Detection, Depth Estimation and Semantic Segmentation
• segDeepM: Exploiting Segmentation and Context in Deep Neural Networks for Object Detection
• Range Loss for Deep Face Recognition with Long-tail
• MoleculeNet: A Benchmark for Molecular Machine Learning
• Edge Intelligence: On-Demand Deep Learning Model Co-Inference with Device-Edge Synergy
• Natural Language Understanding with Distributed Representation
• Photographic Text-to-Image Synthesis with a Hierarchically-nested Adversarial Network
• Pushing the Boundaries of Boundary Detection using Deep Learning
• Deep Learning for Computational Chemistry
• Exploring Hidden Dimensions in Parallelizing Convolutional Neural Networks
• An exploration of parameter redundancy in deep networks with circulant projections
• Interleaved Text/Image Deep Mining on a Large-Scale Radiology Database for Automated Image Interpretation
• Stacked Generative Adversarial Networks
• Deep Learning Convolutional Networks for Multiphoton Microscopy Vasculature Segmentation
• Appearance-and-Relation Networks for Video Classification
• Smart Mining for Deep Metric Learning
• Deep Discriminative Clustering Analysis
• Data Distillation: Towards Omni-Supervised Learning
• An Empirical Study on Writer Identification & Verification from Intra-variable Individual Handwriting
• Combining the Best of Convolutional Layers and Recurrent Layers: A Hybrid Network for Semantic Segmentation
• Separating the EoR Signal with a Convolutional Denoising Autoencoder: A Deep-learning-based Method
• Decision Support System for an Intelligent Operator of Utility Tunnel Boring Machines
• Mobile Video Object Detection with Temporally-Aware Feature Maps
• Deep Spatial Pyramid: The Devil is Once Again in the Details
• A deep architecture for unified aesthetic prediction
• Higher Order Recurrent Neural Networks
• Deep Learning for Semantic Part Segmentation with High-Level Guidance
• HD-CNN: Hierarchical Deep Convolutional Neural Network for Large Scale Visual Recognition
• Bounding Box Regression with Uncertainty for Accurate Object Detection
• Learning Visual Clothing Style with Heterogeneous Dyadic Co-occurrences
• Training Binary Multilayer Neural Networks for Image Classification using Expectation Backpropagation
• Image Question Answering using Convolutional Neural Network with Dynamic Parameter Prediction
• FaceBoxes: A CPU Real-time Face Detector with High Accuracy
• When Face Recognition Meets with Deep Learning: an Evaluation of Convolutional Neural Networks for Face Recognition
• Associative Domain Adaptation
• Untangling Local and Global Deformations in Deep Convolutional Networks for Image Classification and Sliding Window Detection
• SPP-Net: Deep Absolute Pose Regression with Synthetic Views
• Fully Convolutional Networks for Chip-wise Defect Detection Employing Photoluminescence Images
• Multi-scale Deep Learning Architectures for Person Re-identification
• Enhancing Adversarial Example Transferability with an Intermediate Level Attack
• Classification is a Strong Baseline for Deep Metric Learning
• Spectrum-Diverse Neuroevolution with Unified Neural Models
• Machine Learning (In) Security: A Stream of Problems
• Identity-Aware Textual-Visual Matching with Latent Co-attention
• Deep Fingerprinting: Undermining Website Fingerprinting Defenses with Deep Learning
• Unconstrained Facial Landmark Localization with Backbone-Branches Fully-Convolutional Networks
• On Learning to Think: Algorithmic Information Theory for Novel Combinations of Reinforcement Learning Controllers and Recurrent Neural World Models
• Distributed TensorFlow with MPI
• Style Transfer for Anime Sketches with Enhanced Residual U-net and Auxiliary Classifier GAN
• Rethinking the Faster R-CNN Architecture for Temporal Action Localization
• Object Detection Networks on Convolutional Feature Maps
• Compressing Convolutional Neural Networks
• Machine learning for complete intersection Calabi-Yau manifolds: a methodological study
• Quantized Convolutional Neural Networks for Mobile Devices
• Zero-shot Recognition via Semantic Embeddings and Knowledge Graphs
• Learning Deep Neural Networks for Vehicle Re-ID with Visual-spatio-temporal Path Proposals
• Object Detection in Video with Spatiotemporal Sampling Networks
• VidLoc: A Deep Spatio-Temporal Model for 6-DoF Video-Clip Relocalization
• Learning Multiscale Features Directly From Waveforms
• Semantic Object Parsing with Local-Global Long Short-Term Memory
• Adapting Deep Network Features to Capture Psychological Representations
• Deep Convolutional Features for Image Based Retrieval and Scene Categorization
• Traffic Sign Classification Using Deep Inception Based Convolutional Networks
• Jointly Modeling Embedding and Translation to Bridge Video and Language
• Deep Pyramidal Residual Networks
• Convolutional Neural Networks at Constrained Time Cost
• Fusing Multi-Stream Deep Networks for Video Classification
• Wide Compression: Tensor Ring Nets
• High-Resolution Image Inpainting using Multi-Scale Neural Patch Synthesis
• Exploring the Neural Algorithm of Artistic Style
• Regularizing RNNs for Caption Generation by Reconstructing The Past with The Present
• COVID-19 Screening Using Residual Attention Network an Artificial Intelligence Approach
• DeepMRSeg: A convolutional deep neural network for anatomy and abnormality segmentation on MR images
• A Study and Comparison of Human and Deep Learning Recognition Performance Under Visual Distortions
• Modeling Spatial-Temporal Clues in a Hybrid Deep Learning Framework for Video Classification
• Quark-Gluon Jet Discrimination Using Convolutional Neural Networks
• SupportNet: solving catastrophic forgetting in class incremental learning with support data
• Deep Back-Projection Networks For Super-Resolution
• Learning to Detect Human-Object Interactions
• Deep Learning For Face Recognition: A Critical Analysis
• Deep Learning for Skin Lesion Classification
• Models Matter, So Does Training: An Empirical Study of CNNs for Optical Flow Estimation
• Computational Baby Learning
• Beyond Frontal Faces: Improving Person Recognition Using Multiple Cues
• Face Attribute Prediction Using Off-the-Shelf CNN Features
• Abnormality Detection in Mammography using Deep Convolutional Neural Networks
• Multi-Instance Visual-Semantic Embedding
• Fine-grained Categorization and Dataset Bootstrapping using Deep Metric Learning with Humans in the Loop
• Spatially Adaptive Computation Time for Residual Networks
• Soft Proposal Networks for Weakly Supervised Object Localization
• Transfer Learning for Video Recognition with Scarce Training Data for Deep Convolutional Neural Network
• Quantization for Rapid Deployment of Deep Neural Networks
• Pose Embeddings: A Deep Architecture for Learning to Match Human Poses
• Matching-CNN Meets KNN: Quasi-Parametric Human Parsing
• Learning efficient haptic shape exploration with a rigid tactile sensor array
• Factors of Transferability for a Generic ConvNet Representation
• Multimodal Emotion Recognition for One-Minute-Gradual Emotion Challenge
• From Patch to Image Segmentation using Fully Convolutional Networks -- Application to Retinal Images
• Compact Convolutional Neural Network Cascade for Face Detection
• Recovering the Missing Link: Predicting Class-Attribute Associations for Unsupervised Zero-Shot Learning
• What is Holding Back Convnets for Detection?
• Semantically Consistent Regularization for Zero-Shot Recognition
• Deep Learning in Bioinformatics
• Batch Kalman Normalization: Towards Training Deep Neural Networks with Micro-Batches
• Online Open World Recognition
• PPR-FCN: Weakly Supervised Visual Relation Detection via Parallel Pairwise R-FCN
• An Accurate and Real-time Self-blast Glass Insulator Location Method Based On Faster R-CNN and U-net with Aerial Images
• Quantizing Convolutional Neural Networks for Low-Power High-Throughput Inference Engines
• Challenging Environments for Traffic Sign Detection: Reliability Assessment under Inclement Conditions
• Boosting Convolutional Features for Robust Object Proposals
• Exploring Person Context and Local Scene Context for Object Detection
• Material Recognition in the Wild with the Materials in Context Database
• Take it in your stride: Do we need striding in CNNs?
• Transform Network Architectures for Deep Learning based End-to-End Image/Video Coding in Subsampled Color Spaces
• Efficient Large Scale Video Classification
• Deep Learning for Object Saliency Detection and Image Segmentation
• Flip-Rotate-Pooling Convolution and Split Dropout on Convolution Neural Networks for Image Classification
• TorontoCity: Seeing the World with a Million Eyes
• Recognizing American Sign Language Manual Signs from RGB-D Videos
• LabelBank: Revisiting Global Perspectives for Semantic Segmentation
• Zero-Shot Learning with Generative Latent Prototype Model
• Dynamic Computational Time for Visual Attention
• A Large-scale Dataset and Benchmark for Similar Trademark Retrieval
• SimNets: A Generalization of Convolutional Networks
• Full-Resolution Residual Networks for Semantic Segmentation in Street Scenes
• HDF: Hybrid Deep Features for Scene Image Representation
• PredNet and Predictive Coding: A Critical Review
• Dense Optical Flow Prediction from a Static Image
• Borrowing Treasures from the Wealthy: Deep Transfer Learning through Selective Joint Fine-tuning
• An OpenCL(TM) Deep Learning Accelerator on Arria 10
• Improving Interpretability of Deep Neural Networks with Semantic Information
• Deep Fried Convnets
• Examining the Use of Neural Networks for Feature Extraction: A Comparative Analysis using Deep Learning, Support Vector Machines, and K-Nearest Neighbor Classifiers
• Learning Digital Camera Pipeline for Extreme Low-Light Imaging
• Multi-Scale Deep Learning for Estimating Horizontal Velocity Fields on the Solar Surface
• deepSIP: Linking Type Ia Supernova Spectra to Photometric Quantities with Deep Learning
• Structured Binary Neural Networks for Accurate Image Classification and Semantic Segmentation
• Convolutional Neural Network for Stereotypical Motor Movement Detection in Autism
• Generic Feature Learning for Wireless Capsule Endoscopy Analysis
• Adaptive Object Detection Using Adjacency and Zoom Prediction
• The iNaturalist Species Classification and Detection Dataset
• Structured Knowledge Distillation for Dense Prediction
• Graph-Based Classification of Omnidirectional Images
• Rafiki: Machine Learning as an Analytics Service System
• Subcategory-aware Convolutional Neural Networks for Object Proposals and Detection
• Measuring the Transferability of Adversarial Examples
• Adversarial Examples Detection in Deep Networks with Convolutional Filter Statistics
• Art of singular vectors and universal adversarial perturbations
• Pose from Action: Unsupervised Learning of Pose Features based on Motion
• EraseReLU: A Simple Way to Ease the Training of Deep Convolution Neural Networks
• A New Convolutional Network-in-Network Structure and Its Applications in Skin Detection, Semantic Segmentation, and Artifact Reduction
• Coarse-to-Fine Volumetric Prediction for Single-Image 3D Human Pose
• Structured Variational Inference for Simulating Populations of Radio Galaxies
• Cross Domain Knowledge Transfer for Person Re-identification
• Pixel-wise Segmentation of Street with Neural Networks
• Land Use and Land Cover Classification Using Deep Learning Techniques
• Exploring the Design Space of Deep Convolutional Neural Networks at Large Scale
• Visual Discovery at Pinterest
• Multi-Path Feedback Recurrent Neural Network for Scene Parsing
• A Revisit on Deep Hashings for Large-scale Content Based Image Retrieval
• From Dark Matter to Galaxies with Convolutional Neural Networks
• On Periodic Functions as Regularizers for Quantization of Neural Networks
• Multi-Fiber Networks for Video Recognition
• Motion Prediction Under Multimodality with Conditional Stochastic Networks
• Crack Semantic Segmentation using the U-Net with Full Attention Strategy
• A Practical Guide to CNNs and Fisher Vectors for Image Instance Retrieval
• Control Distance IoU and Control Distance IoU Loss Function for Better Bounding Box Regression
• Deep Learning for identifying radiogenomic associations in breast cancer
• Image-based localization using LSTMs for structured feature correlation
• Fused DNN: A deep neural network fusion approach to fast and robust pedestrian detection
• From Image-level to Pixel-level Labeling with Convolutional Networks
• LCNN: Lookup-based Convolutional Neural Network
• Modularized Morphing of Neural Networks
• Estimated Depth Map Helps Image Classification
• Single-Shot Bidirectional Pyramid Networks for High-Quality Object Detection
• An End-to-End Approach to Natural Language Object Retrieval via Context-Aware Deep Reinforcement Learning
• SwitchOut: an Efficient Data Augmentation Algorithm for Neural Machine Translation
• Unsupervised Category Discovery via Looped Deep Pseudo-Task Optimization Using a Large Scale Radiology Image Database
• Coordinating Filters for Faster Deep Neural Networks
• Deep learning for detection of bird vocalisations
• Reversible Recursive Instance-level Object Segmentation
• Learning Structured Inference Neural Networks with Label Relations
• ASP Vision: Optically Computing the First Layer of Convolutional Neural Networks using Angle Sensitive Pixels
• Deep End2End Voxel2Voxel Prediction
• Efficient Deep Neural Networks
• Deep Hashing with Category Mask for Fast Video Retrieval
• Dual Path Networks for Multi-Person Human Pose Estimation
• Recurrent Localization Networks applied to the Lippmann-Schwinger Equation
• Content-Based Video Retrieval in Historical Collections of the German Broadcasting Archive
• A Survey on Deep Domain Adaptation and Tiny Object Detection Challenges, Techniques and Datasets
• Autonomous Deep Learning: A Genetic DCNN Designer for Image Classification
• Learning Visual Features from Large Weakly Supervised Data
• Performing Highly Accurate Predictions Through Convolutional Networks for Actual Telecommunication Challenges
• Exploring Corruption Robustness: Inductive Biases in Vision Transformers and MLP-Mixers
• Convolutional Neural Networks for Shower Energy Prediction in Liquid Argon Time Projection Chambers
• A 4D Light-Field Dataset and CNN Architectures for Material Recognition
• Application of Deep Learning on Predicting Prognosis of Acute Myeloid Leukemia with Cytogenetics, Age, and Mutations
• DeepDeblur: Fast one-step blurry face images restoration
• FASTER Recurrent Networks for Efficient Video Classification
• Towards Automatic Image Editing: Learning to See another You
• Universal Lipschitz Approximation in Bounded Depth Neural Networks
• ActionFlowNet: Learning Motion Representation for Action Recognition
• Learning a Discriminative Filter Bank within a CNN for Fine-grained Recognition
• Feedforward and Recurrent Neural Networks Backward Propagation and Hessian in Matrix Form
• Object-centric Sampling for Fine-grained Image Classification
• Low-Shot Learning with Imprinted Weights
• Fully Point-wise Convolutional Neural Network for Modeling Statistical Regularities in Natural Images
• Analyzing Classifiers: Fisher Vectors and Deep Neural Networks
• Dynamic Capacity Networks
• Super-Resolution with Deep Adaptive Image Resampling
• Right whale recognition using convolutional neural networks
• Object-Scene Convolutional Neural Networks for Event Recognition in Images
• UC Merced Submission to the ActivityNet Challenge 2016
• MarioQA: Answering Questions by Watching Gameplay Videos
• Detecting Overfitting via Adversarial Examples
• Propagating Asymptotic-Estimated Gradients for Low Bitwidth Quantized Neural Networks
• Generative Model with Coordinate Metric Learning for Object Recognition Based on 3D Models
• Aspect-based Opinion Summarization with Convolutional Neural Networks
• Deep 3D Face Identification
• Window-Object Relationship Guided Representation Learning for Generic Object Detections
• XRAI: Better Attributions Through Regions
• Between-class Learning for Image Classification
• Deep Quantization: Encoding Convolutional Activations with Deep Generative Model
• DeepGalaxy: Deducing the Properties of Galaxy Mergers from Images Using Deep Neural Networks
• Real-time Human Pose Estimation from Video with Convolutional Neural Networks
• Deep Class Aware Denoising
• Stochastic Downsampling for Cost-Adjustable Inference and Improved Regularization in Convolutional Networks
• Reducing the Training Time of Neural Networks by Partitioning
• On the efficient representation and execution of deep acoustic models
• Do Normalization Layers in a Deep ConvNet Really Need to Be Distinct?
• Unconstrained Face Verification using Deep CNN Features
• Probabilistic Label Relation Graphs with Ising Models
• ClickBAIT-v2: Training an Object Detector in Real-Time
• Partition Pruning: Parallelization-Aware Pruning for Deep Neural Networks
• On the Depth of Deep Neural Networks: A Theoretical View
• DeepIrisNet2: Learning Deep-IrisCodes from Scratch for Segmentation-Robust Visible Wavelength and Near Infrared Iris Recognition
• Factors in Finetuning Deep Model for object detection
• DAP3D-Net: Where, What and How Actions Occur in Videos?
• Structured Feature Learning for Pose Estimation
• Generative Class-conditional Autoencoders
• Top-down Visual Saliency Guided by Captions
• dMath: A Scalable Linear Algebra and Math Library for Heterogeneous GP-GPU Architectures
• End-to-End Deep Kronecker-Product Matching for Person Re-identification
• Error Correction for Dense Semantic Image Labeling
• Deep Learning for Metagenomic Data: using 2D Embeddings and Convolutional Neural Networks
• Towards High Performance Video Object Detection
• Ensemble-Compression: A New Method for Parallel Training of Deep Neural Networks
• MLtuner: System Support for Automatic Machine Learning Tuning
• Ranked List Loss for Deep Metric Learning
• Abnormality Detection in Musculoskeletal Radiographs with Convolutional Neural Networks(Ensembles) and Performance Optimization
• Scalable Balanced Training of Conditional Generative Adversarial Neural Networks on Image Data
• Transfer Learning for Action Unit Recognition
• Theano-MPI: a Theano-based Distributed Training Framework
• Weakly Supervised Learning with Side Information for Noisy Labeled Images
• Part-Stacked CNN for Fine-Grained Visual Categorization
• Sketch2code: Generating a website from a paper mockup
• Irregular Convolutional Neural Networks
• A Guided Spatial Transformer Network for Histology Cell Differentiation
• Server, server in the cloud. Who is the fairest in the crowd?
• Malaria Likelihood Prediction By Effectively Surveying Households Using Deep Reinforcement Learning
• VIPLFaceNet: An Open Source Deep Face Recognition SDK
• Learning Normalized Inputs for Iterative Estimation in Medical Image Segmentation
• On architectural choices in deep learning: From network structure to gradient convergence and parameter estimation
• Invariant backpropagation: how to train a transformation-invariant neural network
• Multi-velocity neural networks for gesture recognition in videos
• Dual Encoder Fusion U-Net (DEFU-Net) for Cross-manufacturer Chest X-ray Segmentation
• Purine: A bi-graph based deep learning framework
• Deep Transfer Learning for Automated Diagnosis of Skin Lesions from Photographs
• Collaborative Layer-wise Discriminative Learning in Deep Neural Networks
• Improving Image Classification with Location Context
• Semi-Parallel Deep Neural Networks (SPDNN), Convergence and Generalization
• An Attention-Driven Approach of No-Reference Image Quality Assessment
• Superpixel Convolutional Networks using Bilateral Inceptions
• Why Do Deep Neural Networks Still Not Recognize These Images?: A Qualitative Analysis on Failure Cases of ImageNet Classification
• Binarized Convolutional Neural Networks with Separable Filters for Efficient Hardware Acceleration
• Beyond Trade-off: Accelerate FCN-based Face Detector with Higher Accuracy
• On Deep Representation Learning from Noisy Web Images
• Towards Human-Machine Cooperation: Self-supervised Sample Mining for Object Detection
• Energy Confused Adversarial Metric Learning for Zero-Shot Image Retrieval and Clustering
• Predicting Localized Primordial Star Formation with Deep Convolutional Neural Networks
• Unsupervised Transductive Domain Adaptation
• CompressNet: Generative Compression at Extremely Low Bitrates
• A deep learning based multiscale approach to segment cancer area in liver whole slide image
• Automatic Moth Detection from Trap Images for Pest Management
• ResNetX: a more disordered and deeper network architecture
• Predicting Length of Stay in the Intensive Care Unit with Temporal Pointwise Convolutional Networks
• Ancient Painting to Natural Image: A New Solution for Painting Processing
• TRADI: Tracking deep neural network weight distributions for uncertainty estimation
• FaceShapeGene: A Disentangled Shape Representation for Flexible Face Image Editing
• Can deep learning help you find the perfect match?
• Analyzing Stability of Convolutional Neural Networks in the Frequency Domain
• Action Unit Detection with Region Adaptation, Multi-labeling Learning and Optimal Temporal Fusing
• Face Recognition in Unconstrained Conditions: A Systematic Review
• MemNet: Memory-Efficiency Guided Neural Architecture Search with Augment-Trim learning
• Material Classification using Neural Networks
• Less-forgetful Learning for Domain Expansion in Deep Neural Networks
• Multi-Scale DenseNet-Based Electricity Theft Detection
• Butterfly Effect: Bidirectional Control of Classification Performance by Small Additive Perturbation
• Pedestrian Detection with Autoregressive Network Phases
• Compression of Deep Neural Networks on the Fly
• Improved Deep Learning of Object Category using Pose Information
• Target Aware Network Adaptation for Efficient Representation Learning
• A Visual Embedding for the Unsupervised Extraction of Abstract Semantics
• A Fast and Accurate System for Face Detection, Identification, and Verification
• Real Time Fine-Grained Categorization with Accuracy and Interpretability
• MTLE: A Multitask Learning Encoder of Visual Feature Representations for Video and Movie Description
• AutoScaler: Scale-Attention Networks for Visual Correspondence
• In Defense of the Classification Loss for Person Re-Identification
• Reconstruction of Simulation-Based Physical Field by Reconstruction Neural Network Method
• A Model for Medical Diagnosis Based on Plantar Pressure
• NAAQA: A Neural Architecture for Acoustic Question Answering
• Deeply-Supervised CNN for Prostate Segmentation
• Fast Video Classification via Adaptive Cascading of Deep Models
• CNN based texture synthesize with Semantic segment
• Fully Associative Patch-based 1-to-N Matcher for Face Recognition
• On Lipschitz Bounds of General Convolutional Neural Networks
• EEG-Inception: An Accurate and Robust End-to-End Neural Network for EEG-based Motor Imagery Classification
• The VQA-Machine: Learning How to Use Existing Vision Algorithms to Answer New Questions
• Few-Shot Object Recognition from Machine-Labeled Web Images
• Clothing Retrieval with Visual Attention Model
• The Pitfall of Evaluating Performance on Emerging AI Accelerators
• cuConv: A CUDA Implementation of Convolution for CNN Inference
• Deep Imbalanced Attribute Classification using Visual Attention Aggregation
• WaveletNet: Logarithmic Scale Efficient Convolutional Neural Networks for Edge Devices
• What can we learn about CNNs from a large scale controlled object dataset?
• Difficulty Translation in Histopathology Images
• Pornographic Image Recognition via Weighted Multiple Instance Learning
• Rep Works in Speaker Verification
• Learning to Select Pre-Trained Deep Representations with Bayesian Evidence Framework
• Confusing Deep Convolution Networks by Relabelling
• An Overview on Data Representation Learning: From Traditional Feature Learning to Recent Deep Learning
• Dynamic Video Segmentation Network
• Analysis of Big Data Technology for Health Care Services
• (DE)^2 CO: Deep Depth Colorization
• Beyond Planar Symmetry: Modeling human perception of reflection and rotation symmetries in the wild
• Stories in the Eye: Contextual Visual Interactions for Efficient Video to Language Translation
• Improve CAM with Auto-adapted Segmentation and Co-supervised Augmentation
• YouTube-8M Video Understanding Challenge Approach and Applications
• Automatic Discovery, Association Estimation and Learning of Semantic Attributes for a Thousand Categories
• An Automated CNN Recommendation System for Image Classification Tasks
• Filter Bank Regularization of Convolutional Neural Networks
• Query-free Clothing Retrieval via Implicit Relevance Feedback
• Online Detection of Action Start in Untrimmed, Streaming Videos
• A Controller-Recognizer Framework: How necessary is recognition for control?
• Image Matters: Scalable Detection of Offensive and Non-Compliant Content / Logo in Product Images
• Better Exploiting OS-CNNs for Better Event Recognition in Images
• Feature Selective Networks for Object Detection
• Generate Image Descriptions based on Deep RNN and Memory Cells for Images Features
• Scalable and Effective Deep CCA via Soft Decorrelation
• Neural Rejuvenation: Improving Deep Network Training by Enhancing Computational Resource Utilization
• Convolutional Channel Features
• Effects of Dataset properties on the training of GANs
• Wasserstein Introspective Neural Networks
• Deep Saliency with Encoded Low level Distance Map and High Level Features
• Loss Landscape Dependent Self-Adjusting Learning Rates in Decentralized Stochastic Gradient Descent
• The Vulnerability of the Neural Networks Against Adversarial Examples in Deep Learning Algorithms
• Input Aggregated Network for Face Video Representation
• Convolution in Convolution for Network in Network
• Dense neural networks as sparse graphs and the lightning initialization
• Embedded Systems and Computer Vision Techniques utilized in Spray Painting Robots: A Review
• Livewired Neural Networks: Making Neurons That Fire Together Wire Together
• Identification of images of COVID-19 from Chest Computed Tomography (CT) images using Deep learning: Comparing COGNEX VisionPro Deep Learning 1.0 Software with Open Source Convolutional Neural Networks
• LogAvgExp Provides a Principled and Performant Global Pooling Operator
• Adversarial training applied to Convolutional Neural Network for photometric redshift predictions
• Multi-scale recognition with DAG-CNNs
• Convolutional neural networks compression with low rank and sparse tensor decompositions
• Manifestation of Image Contrast in Deep Networks
• Improving Deep Binary Embedding Networks by Order-aware Reweighting of Triplets
• 'Part'ly first among equals: Semantic part-based benchmarking for state-of-the-art object recognition systems
• Multi-Scale Weight Sharing Network for Image Recognition
• Itsy Bitsy SpiderNet: Fully Connected Residual Network for Fraud Detection
• CloudifierNet -- Deep Vision Models for Artificial Image Processing
• What can linear interpolation of neural network loss landscapes tell us?
• 2nd Place Solution to Instance Segmentation of IJCAI 3D AI Challenge 2020
• MCMC Guided CNN Training and Segmentation for Pancreas Extraction
• DeepCompress: Efficient Point Cloud Geometry Compression
• Towards Machine Intelligence
• Visual Recognition of Paper Analytical Device Images for Detection of Falsified Pharmaceuticals
• DeepWheat: Estimating Phenotypic Traits from Crop Images with Deep Learning
• Progress of the Charged Pion Semi-Inclusive Neutrino Charged Current Cross Section in NOvA
• Dermatologist vs Neural Network
• C2G-Net: Exploiting Morphological Properties for Image Classification
• Deep Weakly Supervised Positioning
• A Deep Learning Framework for Hydrogen-fueled Turbulent Combustion Simulation
• Liquified protein vibrations, classification and cross-paradigm de novo image generation using deep neural networks
• Towards ECDSA key derivation from deep embeddings for novel Blockchain applications
• Node Specificity in Convolutional Deep Nets Depends on Receptive Field Position and Size
• Multiple Instance Learning Convolutional Neural Networks for Object Recognition
• Diagnosis of Pediatric Obstructive Sleep Apnea via Face Classification with Persistent Homology and Convolutional Neural Networks
• Learning Discriminative Features with Class Encoder
• Leveraging Model Interpretability and Stability to increase Model Robustness
• Investigations of the Influences of a CNN's Receptive Field on Segmentation of Subnuclei of Bilateral Amygdalae
• Warp: a method for neural network interpretability applied to gene expression profiles
• Now that I can see, I can improve: Enabling data-driven finetuning of CNNs on the edge
• Evaluating (and improving) the correspondence between deep neural networks and human representations
• Crowding in humans is unlike that in convolutional neural networks
• Compact retail shelf segmentation for mobile deployment
• Multiple Kernel Learning and Automatic Subspace Relevance Determination for High-dimensional Neuroimaging Data
• Knee menisci segmentation and relaxometry of 3D ultrashort echo time (UTE) cones MR imaging using attention U-Net with transfer learning
• Mediated Experts for Deep Convolutional Networks
• OOWL500: Overcoming Dataset Collection Bias in the Wild
• TUNet: Incorporating segmentation maps to improve classification
• Convolutional neural networks model improvements using demographics and image processing filters on chest x-rays
• Identifying the Absorption Bump with Deep Learning
• A Discriminative Learned CNN Embedding for Remote Sensing Image Scene Classification