Fully Convolutional Networks for Semantic Segmentation

Abstract

Convolutional networks are powerful visual models that yield hierarchies of features. We show that convolutional networks by themselves, trained end-to-end, pixels-to-pixels, exceed the state-of-the-art in semantic segmentation. Our key insight is to build "fully convolutional" networks that take input of arbitrary size and produce correspondingly-sized output with efficient inference and learning. We define and detail the space of fully convolutional networks, explain their application to spatially dense prediction tasks, and draw connections to prior models. We adapt contemporary classification networks (AlexNet, the VGG net, and GoogLeNet) into fully convolutional networks and transfer their learned representations by fine-tuning to the segmentation task. We then define a novel architecture that combines semantic information from a deep, coarse layer with appearance information from a shallow, fine layer to produce accurate and detailed segmentations. Our fully convolutional network achieves state-of-the-art segmentation of PASCAL VOC (20% relative improvement to 62.2% mean IU on 2012), NYUDv2, and SIFT Flow, while inference takes one third of a second for a typical image.

to appear in CVPR (2015)

Cited by in corpus (426)

• A Survey on Deep Learning in Medical Image Analysis
• Convolutional LSTM Network: A Machine Learning Approach for Precipitation Nowcasting
• Semantic Image Segmentation with Deep Convolutional Nets and Fully Connected CRFs
• Efficient Multi-Scale 3D CNN with Fully Connected CRF for Accurate Brain Lesion Segmentation
• Res2Net: A New Multi-scale Backbone Architecture
• Brain Tumor Segmentation with Deep Neural Networks
• Deep Convolutional Neural Network for Inverse Problems in Imaging
• MultiResUNet : Rethinking the U-Net Architecture for Multimodal Biomedical Image Segmentation
• Object Detection in Optical Remote Sensing Images: A Survey and A New Benchmark
• U-Net and its variants for medical image segmentation: theory and applications
• Deep Learning in Spiking Neural Networks
• Deep Multi-modal Object Detection and Semantic Segmentation for Autonomous Driving: Datasets, Methods, and Challenges
• Learning Depth from Single Monocular Images Using Deep Convolutional Neural Fields
• Deep Learning for Single Image Super-Resolution: A Brief Review
• UIU-Net: U-Net in U-Net for Infrared Small Object Detection
• ShuffleNet: An Extremely Efficient Convolutional Neural Network for Mobile Devices
• Interactive Medical Image Segmentation using Deep Learning with Image-specific Fine-tuning
• A Deep Learning Framework for Unsupervised Affine and Deformable Image Registration
• Medical Image Segmentation Using Deep Learning: A Survey
• Richer Convolutional Features for Edge Detection
• Deep neural network models for computational histopathology: A survey
• Anabranch Network for Camouflaged Object Segmentation
• Bayesian Deep Convolutional Encoder-Decoder Networks for Surrogate Modeling and Uncertainty Quantification
• Deeply supervised salient object detection with short connections
• A review: Deep learning for medical image segmentation using multi-modality fusion
• Aleatoric uncertainty estimation with test-time augmentation for medical image segmentation with convolutional neural networks
• Video Salient Object Detection via Fully Convolutional Networks
• Automatic Liver and Lesion Segmentation in CT Using Cascaded Fully Convolutional Neural Networks and 3D Conditional Random Fields
• A Survey of Recent Advances in CNN-based Single Image Crowd Counting and Density Estimation
• STC: A Simple to Complex Framework for Weakly-supervised Semantic Segmentation
• HDR image reconstruction from a single exposure using deep CNNs
• T-CNN: Tubelets with Convolutional Neural Networks for Object Detection from Videos
• DeepSaliency: Multi-Task Deep Neural Network Model for Salient Object Detection
• Curriculum Domain Adaptation for Semantic Segmentation of Urban Scenes
• Human pose estimation via Convolutional Part Heatmap Regression
• Deep Label Distribution Learning with Label Ambiguity
• Fully Dense UNet for 2D Sparse Photoacoustic Tomography Artifact Removal
• Denoising Prior Driven Deep Neural Network for Image Restoration
• Boundary loss for highly unbalanced segmentation
• DeepIGeoS: A Deep Interactive Geodesic Framework for Medical Image Segmentation
• Eigen-CAM: Class Activation Map using Principal Components
• Hybrid LSTM and Encoder-Decoder Architecture for Detection of Image Forgeries
• RA-UNet: A hybrid deep attention-aware network to extract liver and tumor in CT scans
• Convolutional Feature Masking for Joint Object and Stuff Segmentation
• DeepNIS: Deep Neural Network for Nonlinear Electromagnetic Inverse Scattering
• Classifying and Segmenting Microscopy Images Using Convolutional Multiple Instance Learning
• Monocular Human Pose Estimation: A Survey of Deep Learning-based Methods
• Optic Disc and Cup Segmentation Methods for Glaucoma Detection with Modification of U-Net Convolutional Neural Network
• 3D fully convolutional networks for subcortical segmentation in MRI: A large-scale study
• Optimization for Medical Image Segmentation: Theory and Practice when evaluating with Dice Score or Jaccard Index
• A Novel Transformer Based Semantic Segmentation Scheme for Fine-Resolution Remote Sensing Images
• Real-Time Polyp Detection, Localization and Segmentation in Colonoscopy Using Deep Learning
• A deep-learning-based surrogate model for data assimilation in dynamic subsurface flow problems
• An In-field Automatic Wheat Disease Diagnosis System
• TextField: Learning A Deep Direction Field for Irregular Scene Text Detection
• Path Aggregation Network for Instance Segmentation
• MVSS-Net: Multi-View Multi-Scale Supervised Networks for Image Manipulation Detection
• MILD-Net: Minimal Information Loss Dilated Network for Gland Instance Segmentation in Colon Histology Images
• Association of genomic subtypes of lower-grade gliomas with shape features automatically extracted by a deep learning algorithm
• An application of cascaded 3D fully convolutional networks for medical image segmentation
• Supervised Learning of Semantics-Preserving Hash via Deep Convolutional Neural Networks
• Multimodal End-to-End Autonomous Driving
• Layer-Wise Relevance Propagation for Explaining Deep Neural Network Decisions in MRI-Based Alzheimer's Disease Classification
• Foreground Segmentation Using a Triplet Convolutional Neural Network for Multiscale Feature Encoding
• Retinal vessel segmentation based on Fully Convolutional Neural Networks
• FusionNet: A deep fully residual convolutional neural network for image segmentation in connectomics
• SCAttNet: Semantic Segmentation Network with Spatial and Channel Attention Mechanism for High-Resolution Remote Sensing Images
• Semantic Labeling in Very High Resolution Images via a Self-Cascaded Convolutional Neural Network
• DeepLOB: Deep Convolutional Neural Networks for Limit Order Books
• Design of Task-Specific Optical Systems Using Broadband Diffractive Neural Networks
• Land cover mapping at very high resolution with rotation equivariant CNNs: towards small yet accurate models
• Fully Convolutional Networks with Sequential Information for Robust Crop and Weed Detection in Precision Farming
• Uncertainty-aware multi-view co-training for semi-supervised medical image segmentation and domain adaptation
• XSleepNet: Multi-View Sequential Model for Automatic Sleep Staging
• Learning Optimal Resource Allocations in Wireless Systems
• Visual Question Answering: Datasets, Algorithms, and Future Challenges
• Automatic calcium scoring in low-dose chest CT using deep neural networks with dilated convolutions
• X-ModalNet: A Semi-Supervised Deep Cross-Modal Network for Classification of Remote Sensing Data
• Boundary-aware Context Neural Network for Medical Image Segmentation
• Abdominal multi-organ segmentation with organ-attention networks and statistical fusion
• Modality specific U-Net variants for biomedical image segmentation: A survey
• Building extraction with vision transformer
• Embedding Structured Contour and Location Prior in Siamesed Fully Convolutional Networks for Road Detection
• Fully Convolutional Network Ensembles for White Matter Hyperintensities Segmentation in MR Images
• A Survey on Deep Learning-based Architectures for Semantic Segmentation on 2D images
• Region Convolutional Features for Multi-Label Remote Sensing Image Retrieval
• Bi-Temporal Semantic Reasoning for the Semantic Change Detection in HR Remote Sensing Images
• Lunar Crater Identification via Deep Learning
• GridMask Data Augmentation
• Contextual Encoder-Decoder Network for Visual Saliency Prediction
• Fruit Detection, Segmentation and 3D Visualisation of Environments in Apple Orchards
• Deep learning analysis of the myocardium in coronary CT angiography for identification of patients with functionally significant coronary artery stenosis
• DeepIM: Deep Iterative Matching for 6D Pose Estimation
• CrackGAN: Pavement Crack Detection Using Partially Accurate Ground Truths Based on Generative Adversarial Learning
• Progressive LiDAR Adaptation for Road Detection
• Convolutional neural networks automate detection for tracking of submicron scale particles in 2D and 3D
• Road Segmentation in SAR Satellite Images with Deep Fully-Convolutional Neural Networks
• Landslide4Sense: Reference Benchmark Data and Deep Learning Models for Landslide Detection
• A Survey of Human Activity Recognition in Smart Homes Based on IoT Sensors Algorithms: Taxonomies, Challenges, and Opportunities with Deep Learning
• Deep Aesthetic Quality Assessment with Semantic Information
• Recurrently Exploring Class-wise Attention in A Hybrid Convolutional and Bidirectional LSTM Network for Multi-label Aerial Image Classification
• Multi-branch Convolutional Neural Network for Multiple Sclerosis Lesion Segmentation
• Slice-to-volume medical image registration: a survey
• Applications of Deep Learning Techniques for Automated Multiple Sclerosis Detection Using Magnetic Resonance Imaging: A Review
• Gland Instance Segmentation Using Deep Multichannel Neural Networks
• Super-resolution-based Change Detection Network with Stacked Attention Module for Images with Different Resolutions
• Adversarial Example Detection for DNN Models: A Review and Experimental Comparison
• Semantic Image Segmentation via Deep Parsing Network
• A Comparative Study of Fruit Detection and Counting Methods for Yield Mapping in Apple Orchards
• Hybrid CNN and Dictionary-Based Models for Scene Recognition and Domain Adaptation
• AxonDeepSeg: automatic axon and myelin segmentation from microscopy data using convolutional neural networks
• Deep learning for detection and segmentation of artefact and disease instances in gastrointestinal endoscopy
• Origami: A 803 GOp/s/W Convolutional Network Accelerator
• RGB-D Object Detection and Semantic Segmentation for Autonomous Manipulation in Clutter
• Automatic Brain Tumor Segmentation using Convolutional Neural Networks with Test-Time Augmentation
• DISC: Deep Image Saliency Computing via Progressive Representation Learning
• Cross-Domain Visual Matching via Generalized Similarity Measure and Feature Learning
• End-to-End Photo-Sketch Generation via Fully Convolutional Representation Learning
• Looking Outside the Window: Wide-Context Transformer for the Semantic Segmentation of High-Resolution Remote Sensing Images
• Affinity Attention Graph Neural Network for Weakly Supervised Semantic Segmentation
• Neonatal seizure detection from raw multi-channel EEG using a fully convolutional architecture
• BS-Net: learning COVID-19 pneumonia severity on a large Chest X-Ray dataset
• CaraNet: Context Axial Reverse Attention Network for Segmentation of Small Medical Objects
• MirrorNet: Bio-Inspired Camouflaged Object Segmentation
• X-Net: Brain Stroke Lesion Segmentation Based on Depthwise Separable Convolution and Long-range Dependencies
• Deep Shading: Convolutional Neural Networks for Screen-Space Shading
• An evidential classifier based on Dempster-Shafer theory and deep learning
• Vision-based Real Estate Price Estimation
• DCAN: Deep Contour-Aware Networks for Accurate Gland Segmentation
• Traffic Surveillance Camera Calibration by 3D Model Bounding Box Alignment for Accurate Vehicle Speed Measurement
• Multi-Scale Supervised 3D U-Net for Kidneys and Kidney Tumor Segmentation
• 3D Sketching using Multi-View Deep Volumetric Prediction
• Edge Preserving and Multi-Scale Contextual Neural Network for Salient Object Detection
• BiSeNet: Bilateral Segmentation Network for Real-time Semantic Segmentation
• End2End Occluded Face Recognition by Masking Corrupted Features
• Geometry-Aware Fruit Grasping Estimation for Robotic Harvesting in Orchards
• Weakly Supervised Deep Learning for Thoracic Disease Classification and Localization on Chest X-rays
• Reinventing 2D Convolutions for 3D Images
• Multi-Spectral Image Synthesis for Crop/Weed Segmentation in Precision Farming
• Deep-Learning-Enabled Fast Optical Identification and Characterization of Two-Dimensional Materials
• EAST: An Efficient and Accurate Scene Text Detector
• An Attention-Guided Deep Regression Model for Landmark Detection in Cephalograms
• Analysis of the hands in egocentric vision: A survey
• Deep convolutional neural networks for segmenting 3D in vivo multiphoton images of vasculature in Alzheimer disease mouse models
• Mapping horizontal and vertical urban densification in Denmark with Landsat time-series from 1985 to 2018: a semantic segmentation solution
• Dynamic Fusion Module Evolves Drivable Area and Road Anomaly Detection: A Benchmark and Algorithms
• Unsupervised Domain Adaptation with Adversarial Residual Transform Networks
• Joint Vertebrae Identification and Localization in Spinal CT Images by Combining Short- and Long-Range Contextual Information
• MFSNet: A Multi Focus Segmentation Network for Skin Lesion Segmentation
• ZoomNeXt: A Unified Collaborative Pyramid Network for Camouflaged Object Detection
• DeepSkeleton: Learning Multi-task Scale-associated Deep Side Outputs for Object Skeleton Extraction in Natural Images
• FECANet: Boosting Few-Shot Semantic Segmentation with Feature-Enhanced Context-Aware Network
• Automated Evaluation of Semantic Segmentation Robustness for Autonomous Driving
• Visual Perception and Modelling in Unstructured Orchard for Apple Harvesting Robots
• A Survey of Knowledge Representation in Service Robotics
• Deep multi-task learning for a geographically-regularized semantic segmentation of aerial images
• Hierarchical Paired Channel Fusion Network for Street Scene Change Detection
• Real-Time Automatic Fetal Brain Extraction in Fetal MRI by Deep Learning
• Segmentation of Lungs in Chest X-Ray Image Using Generative Adversarial Networks
• FocusNetv2: Imbalanced Large and Small Organ Segmentation with Adversarial Shape Constraint for Head and Neck CT Images
• Artificial Intelligent Atomic Force Microscope Enabled by Machine Learning
• Review of data analysis in vision inspection of power lines with an in-depth discussion of deep learning technology
• Optimized Deep Encoder-Decoder Methods for Crack Segmentation
• Learning Self-Supervised Low-Rank Network for Single-Stage Weakly and Semi-Supervised Semantic Segmentation
• WaferSegClassNet -- A Light-weight Network for Classification and Segmentation of Semiconductor Wafer Defects
• Accelerator-Aware Pruning for Convolutional Neural Networks
• Learning Deformable Registration of Medical Images with Anatomical Constraints
• Multiclass Weighted Loss for Instance Segmentation of Cluttered Cells
• Multi-views Fusion CNN for Left Ventricular Volumes Estimation on Cardiac MR Images
• Dynamic Sampling Networks for Efficient Action Recognition in Videos
• Faster Training of Mask R-CNN by Focusing on Instance Boundaries
• FEA-Net: A Physics-guided Data-driven Model for Efficient Mechanical Response Prediction
• LiteSeg: A Novel Lightweight ConvNet for Semantic Segmentation
• BGnet: Accurate and rapid background estimation in single-molecule localization microscopy with deep neural nets
• A Method of Rapid Quantification of Patient-Specific Organ Dose for CT Using Coupled Deep-Learning based Multi-Organ Segmentation and GPU-accelerated Monte Carlo Dose Computing
• ConnNet: A Long-Range Relation-Aware Pixel-Connectivity Network for Salient Segmentation
• Net2Vis -- A Visual Grammar for Automatically Generating Publication-Tailored CNN Architecture Visualizations
• Three Dimensional Fluorescence Microscopy Image Synthesis and Segmentation
• Recurrent Neural Networks to Correct Satellite Image Classification Maps
• Multi-Modal Mutual Attention and Iterative Interaction for Referring Image Segmentation
• Depth Adaptive Deep Neural Network for Semantic Segmentation
• Convolutional Neural Networks with Intermediate Loss for 3D Super-Resolution of CT and MRI Scans
• PU-Net: Point Cloud Upsampling Network
• MudrockNet: Semantic Segmentation of Mudrock SEM Images through Deep Learning
• Few-Shot Learning with Geometric Constraints
• Generalized Domain Conditioned Adaptation Network
• PhenoBench -- A Large Dataset and Benchmarks for Semantic Image Interpretation in the Agricultural Domain
• UVid-Net: Enhanced Semantic Segmentation of UAV Aerial Videos by Embedding Temporal Information
• Urban Land Cover Classification with Missing Data Modalities Using Deep Convolutional Neural Networks
• Stage-Aware Feature Alignment Network for Real-Time Semantic Segmentation of Street Scenes
• Dynamic Facial Expression Generation on Hilbert Hypersphere with Conditional Wasserstein Generative Adversarial Nets
• Multi-Task Learning of Height and Semantics from Aerial Images
• Salient Object Detection with Lossless Feature Reflection and Weighted Structural Loss
• PAD-Net: Multi-Tasks Guided Prediction-and-Distillation Network for Simultaneous Depth Estimation and Scene Parsing
• Analyzing Modular CNN Architectures for Joint Depth Prediction and Semantic Segmentation
• Consistency-Regularized Region-Growing Network for Semantic Segmentation of Urban Scenes with Point-Level Annotations
• Gastric histopathology image segmentation using a hierarchical conditional random field
• Estimation of the volume of the left ventricle from MRI images using deep neural networks
• Improving Variational Autoencoder with Deep Feature Consistent and Generative Adversarial Training
• Feature Pyramid and Hierarchical Boosting Network for Pavement Crack Detection
• Pancreas segmentation with probabilistic map guided bi-directional recurrent UNet
• J-MOD${}^2$: Joint Monocular Obstacle Detection and Depth Estimation
• Deep Learning Approach for Building Detection in Satellite Multispectral Imagery
• Dual Adaptive Representation Alignment for Cross-domain Few-shot Learning
• TopicFM: Robust and Interpretable Topic-Assisted Feature Matching
• One-Two-One Networks for Compression Artifacts Reduction in Remote Sensing
• Multi-task fully convolutional network for tree species mapping in dense forests using small training hyperspectral data
• Listening for Sirens: Locating and Classifying Acoustic Alarms in City Scenes
• A Unified Framework for Generalized Low-Shot Medical Image Segmentation with Scarce Data
• Towards Image-based Automatic Meter Reading in Unconstrained Scenarios: A Robust and Efficient Approach
• Deep Learning Fetal Ultrasound Video Model Match Human Observers in Biometric Measurements
• Automatic catheter detection in pediatric X-ray images using a scale-recurrent network and synthetic data
• A convolutional autoencoder approach for mining features in cellular electron cryo-tomograms and weakly supervised coarse segmentation
• CovTANet: A Hybrid Tri-level Attention Based Network for Lesion Segmentation, Diagnosis, and Severity Prediction of COVID-19 Chest CT Scans
• Fast and Accurate Road Crack Detection Based on Adaptive Cost-Sensitive Loss Function
• DAN-Net: Dual-Domain Adaptive-Scaling Non-local Network for CT Metal Artifact Reduction
• Knowledge-aware Deep Framework for Collaborative Skin Lesion Segmentation and Melanoma Recognition
• Bi-directional Cross-Modality Feature Propagation with Separation-and-Aggregation Gate for RGB-D Semantic Segmentation
• DFTerNet: Towards 2-bit Dynamic Fusion Networks for Accurate Human Activity Recognition
• Video Semantic Segmentation with Distortion-Aware Feature Correction
• On Support Relations and Semantic Scene Graphs
• MGNet: Monocular Geometric Scene Understanding for Autonomous Driving
• Deep convolutional neural networks for multi-planar lung nodule detection: improvement in small nodule identification
• Inspect, Understand, Overcome: A Survey of Practical Methods for AI Safety
• Spatio-Temporal Point Process for Multiple Object Tracking
• Any Way You Look At It: Semantic Crossview Localization and Mapping with LiDAR
• ZNN - A Fast and Scalable Algorithm for Training 3D Convolutional Networks on Multi-Core and Many-Core Shared Memory Machines
• A fully end-to-end deep learning approach for real-time simultaneous 3D reconstruction and material recognition
• Salient Object Detection via Dynamic Scale Routing
• Unsupervised Semantic-based Aggregation of Deep Convolutional Features
• Estimating Color-Concept Associations from Image Statistics
• Convolutional Neural Nets in Chemical Engineering: Foundations, Computations, and Applications
• TernaryNet: Faster Deep Model Inference without GPUs for Medical 3D Segmentation using Sparse and Binary Convolutions
• Deep Slow Motion Video Reconstruction with Hybrid Imaging System
• Lesion Segmentation in Ultrasound Using Semi-pixel-wise Cycle Generative Adversarial Nets
• A Two-Stream Symmetric Network with Bidirectional Ensemble for Aerial Image Matching
• Compensating for visibility artefacts in photoacoustic imaging with a deep learning approach providing prediction uncertainties
• A Comprehensive Review of Modern Object Segmentation Approaches
• The Stixel world: A medium-level representation of traffic scenes
• Deep Multi-Branch Aggregation Network for Real-Time Semantic Segmentation in Street Scenes
• Brain Tumor Synthetic Segmentation in 3D Multimodal MRI Scans
• Incorporating Network Built-in Priors in Weakly-supervised Semantic Segmentation
• Learning Deep Similarity Models with Focus Ranking for Fabric Image Retrieval
• Attention guided global enhancement and local refinement network for semantic segmentation
• Learning to Label Seismic Structures with Deconvolution Networks and Weak Labels
• SemanticVoxels: Sequential Fusion for 3D Pedestrian Detection using LiDAR Point Cloud and Semantic Segmentation
• Adaptive Image Sampling using Deep Learning and its Application on X-Ray Fluorescence Image Reconstruction
• Hierarchical binary CNNs for landmark localization with limited resources
• Anchor Cascade for Efficient Face Detection
• Fully Convolutional Networks for Chip-wise Defect Detection Employing Photoluminescence Images
• MT-UDA: Towards Unsupervised Cross-modality Medical Image Segmentation with Limited Source Labels
• Incremental Few-Shot Semantic Segmentation via Embedding Adaptive-Update and Hyper-class Representation
• LDNet: End-to-End Lane Marking Detection Approach Using a Dynamic Vision Sensor
• Cut-Thumbnail: A Novel Data Augmentation for Convolutional Neural Network
• Deep learning-based photoacoustic imaging of vascular network through thick porous media
• CT-Net: Arbitrary-Shaped Text Detection via Contour Transformer
• A Deep Learning Approach for Pose Estimation from Volumetric OCT Data
• H-CNN: Spatial Hashing Based CNN for 3D Shape Analysis
• Dual Branch Neural Network for Sea Fog Detection in Geostationary Ocean Color Imager
• A Learning Framework for n-bit Quantized Neural Networks toward FPGAs
• CiT-Net: Convolutional Neural Networks Hand in Hand with Vision Transformers for Medical Image Segmentation
• Deeply Self-Supervised Contour Embedded Neural Network Applied to Liver Segmentation
• Learning Inductive Attention Guidance for Partially Supervised Pancreatic Ductal Adenocarcinoma Prediction
• PIG-Net: Inception based Deep Learning Architecture for 3D Point Cloud Segmentation
• A Machine Learning Surrogate Modeling Benchmark for Temperature Field Reconstruction of Heat-Source Systems
• StressNAS: Affect State and Stress Detection Using Neural Architecture Search
• Panoptic Instance Segmentation on Pigs
• Deep Co-supervision and Attention Fusion Strategy for Automatic COVID-19 Lung Infection Segmentation on CT Images
• Automatic recognition of element classes and boundaries in the birdsong with variable sequences
• Survey on Vision-based Path Prediction
• Scoring and Assessment in Medical VR Training Simulators with Dynamic Time Series Classification
• The Impact of Preprocessing on Deep Representations for Iris Recognition on Unconstrained Environments
• Deep Learning-Guided Surface Characterization for Autonomous Hydrogen Lithography
• ClipGen: A Deep Generative Model for Clipart Vectorization and Synthesis
• Mask-aware Photorealistic Face Attribute Manipulation
• TextDCT: Arbitrary-Shaped Text Detection via Discrete Cosine Transform Mask
• Pediatric Automatic Sleep Staging: A comparative study of state-of-the-art deep learning methods
• Joint Object and Part Segmentation using Deep Learned Potentials
• AuxNet: Auxiliary tasks enhanced Semantic Segmentation for Automated Driving
• SkipConvGAN: Monaural Speech Dereverberation using Generative Adversarial Networks via Complex Time-Frequency Masking
• Acceleration and Quantitation of Localized Correlated Spectroscopy using Deep Learning: A Pilot Simulation Study
• Geometry in Active Learning for Binary and Multi-class Image Segmentation
• Relative Feature Importance
• Evaluation of the potential of Near Infrared Hyperspectral Imaging for monitoring the invasive brown marmorated stink bug
• Semi-Supervised Building Footprint Generation with Feature and Output Consistency Training
• PS^2-Net: A Locally and Globally Aware Network for Point-Based Semantic Segmentation
• Density-based clustering with fully-convolutional networks for crowd flow detection from drones
• Objectness Scoring and Detection Proposals in Forward-Looking Sonar Images with Convolutional Neural Networks
• Reducing the Model Variance of a Rectal Cancer Segmentation Network
• Exploiting Shape Cues for Weakly Supervised Semantic Segmentation
• Smart Scribbles for Image Mating
• RSI-Net: Two-Stream Deep Neural Network for Remote Sensing Imagesbased Semantic Segmentation
• Discriminative Training of Deep Fully-connected Continuous CRF with Task-specific Loss
• A modular U-Net for automated segmentation of X-ray tomography images in composite materials
• Multi-modal land cover mapping of remote sensing images using pyramid attention and gated fusion networks
• Motion Estimation in Occupancy Grid Maps in Stationary Settings Using Recurrent Neural Networks
• An efficient solution for semantic segmentation: ShuffleNet V2 with atrous separable convolutions
• RED: A ReRAM-based Deconvolution Accelerator
• Automatic Borescope Damage Assessments for Gas Turbine Blades via Deep Learning
• Vehicle Perception from Satellite
• Generative Models Improve Radiomics Reproducibility in Low Dose CTs: A Simulation Study
• Adapting Semantic Segmentation Models for Changes in Illumination and Camera Perspective
• Birds of A Feather Flock Together: Category-Divergence Guidance for Domain Adaptive Segmentation
• ORDNet: Capturing Omni-Range Dependencies for Scene Parsing
• InfiNet: Fully Convolutional Networks for Infant Brain MRI Segmentation
• Lightweight Residual Densely Connected Convolutional Neural Network
• Pneumothorax Segmentation: Deep Learning Image Segmentation to predict Pneumothorax
• Towards Interpretable and Robust Hand Detection via Pixel-wise Prediction
• Conquering Data Variations in Resolution: A Slice-Aware Multi-Branch Decoder Network
• Distribution-aware Margin Calibration for Semantic Segmentation in Images
• Continual Coarse-to-Fine Domain Adaptation in Semantic Segmentation
• SceneAdapt: Scene-based domain adaptation for semantic segmentation using adversarial learning
• Multi-Modal Multi-Task (3MT) Road Segmentation
• Global Aggregation then Local Distribution for Scene Parsing
• Learning Densities in Feature Space for Reliable Segmentation of Indoor Scenes
• Tackling the Challenges in Scene Graph Generation with Local-to-Global Interactions
• Weakly Supervised Change Detection Using Guided Anisotropic Difusion
• Microparticle cloud imaging and tracking for data-driven plasma science
• Label-guided Attention Distillation for Lane Segmentation
• Toward Intelligent and Efficient 6G Networks: JCSC Enabled On-Purpose Machine Communications
• Iterative Multi-domain Regularized Deep Learning for Anatomical Structure Detection and Segmentation from Ultrasound Images
• Theoretical analysis and experimental validation of volume bias of soft Dice optimized segmentation maps in the context of inherent uncertainty
• DMTNet: Dynamic Multi-scale Network for Dual-pixel Images Defocus Deblurring with Transformer
• Vicinal and categorical domain adaptation
• Central object segmentation by deep learning for fruits and other roundish objects
• Self-supervised Assisted Active Learning for Skin Lesion Segmentation
• Shallow2Deep: Indoor Scene Modeling by Single Image Understanding
• Deep Attention-guided Hashing
• Graph-Segmenter: Graph Transformer with Boundary-aware Attention for Semantic Segmentation
• LSENet: Location and Seasonality Enhanced Network for Multi-Class Ocean Front Detection
• Topology-preserving Scan-based Immersed Isogeometric Analysis
• A Flexible Selection Scheme for Minimum-Effort Transfer Learning
• Learning-based Defect Recognition for Quasi-Periodic Microscope Images
• PRSeg: A Lightweight Patch Rotate MLP Decoder for Semantic Segmentation
• Online Continual Learning via the Knowledge Invariant and Spread-out Properties
• Weakly-supervised Learning For Catheter Segmentation in 3D Frustum Ultrasound
• Unsupervised Online Learning for Robotic Interestingness with Visual Memory
• AdaStereo: A Simple and Efficient Approach for Adaptive Stereo Matching
• Robust deep learning for emulating turbulent viscosities
• Crowd-Sourced NeRF: Collecting Data from Production Vehicles for 3D Street View Reconstruction
• Deep-Energy: Unsupervised Training of Deep Neural Networks
• Learning Dynamic Routing for Semantic Segmentation
• Training Invertible Neural Networks as Autoencoders
• Learning Deep Representations for Semantic Image Parsing: a Comprehensive Overview
• Learning Motion and Temporal Cues for Unsupervised Video Object Segmentation
• Co-Training for Unsupervised Domain Adaptation of Semantic Segmentation Models
• DenseAttentionSeg: Segment Hands from Interacted Objects Using Depth Input
• Learning Pneumatic Non-Prehensile Manipulation with a Mobile Blower
• FxP-QNet: A Post-Training Quantizer for the Design of Mixed Low-Precision DNNs with Dynamic Fixed-Point Representation
• PetroSurf3D - A Dataset for high-resolution 3D Surface Segmentation
• Tensor Low-Rank Reconstruction for Semantic Segmentation
• Describe me if you can! Characterized Instance-level Human Parsing
• Generating Hard Examples for Pixel-wise Classification
• Deep learning-based super-resolution fluorescence microscopy on small datasets
• ACT-Net: Asymmetric Co-Teacher Network for Semi-supervised Memory-efficient Medical Image Segmentation
• Building Footprint Extraction with Graph Convolutional Network
• Meta-hallucinator: Towards Few-Shot Cross-Modality Cardiac Image Segmentation
• Real-time Fusion Network for RGB-D Semantic Segmentation Incorporating Unexpected Obstacle Detection for Road-driving Images
• End-to-end depth from motion with stabilized monocular videos
• Amplitude Spectrum Transformation for Open Compound Domain Adaptive Semantic Segmentation
• Multi-Slice Dense-Sparse Learning for Efficient Liver and Tumor Segmentation
• Rapid Exact Signal Scanning with Deep Convolutional Neural Networks
• Boosting Binary Masks for Multi-Domain Learning through Affine Transformations
• Search for the edge-on galaxies using an artificial neural network
• Data Stream Stabilization for Optical Coherence Tomography Volumetric Scanning
• Generative Model with Coordinate Metric Learning for Object Recognition Based on 3D Models
• Propagating Asymptotic-Estimated Gradients for Low Bitwidth Quantized Neural Networks
• SemSegDepth: A Combined Model for Semantic Segmentation and Depth Completion
• Learning to Predict Context-adaptive Convolution for Semantic Segmentation
• An Attention-Based Deep Generative Model for Anomaly Detection in Industrial Control Systems
• Adversarial Image Generation by Spatial Transformation in Perceptual Colorspaces
• Adaptive Object Detection with Dual Multi-Label Prediction
• RA V-Net: Deep learning network for automated liver segmentation
• Measuring economic activity from space: a case study using flying airplanes and COVID-19
• DISIR: Deep Image Segmentation with Interactive Refinement
• 3D-to-2D Distillation for Indoor Scene Parsing
• TW-SMNet: Deep Multitask Learning of Tele-Wide Stereo Matching
• Improving Road Segmentation in Challenging Domains Using Similar Place Priors
• GRIP: Generative Robust Inference and Perception for Semantic Robot Manipulation in Adversarial Environments
• Transfer Learning for Ultrasound Tongue Contour Extraction with Different Domains
• Efficient learning of goal-oriented push-grasping synergy in clutter
• A comparative study of source-finding techniques in HI emission line cubes using SoFiA, MTObjects, and supervised deep learning
• Exploration of Convolutional Neural Network Architectures for Large Region Map Automation
• FNA++: Fast Network Adaptation via Parameter Remapping and Architecture Search
• Dual Encoder Fusion U-Net (DEFU-Net) for Cross-manufacturer Chest X-ray Segmentation
• Ground Truth Simulation for Deep Learning Classification of Mid-Resolution Venus Images Via Unmixing of High-Resolution Hyperspectral Fenix Data
• Simultaneous Segmentation and Relaxometry for MRI through Multitask Learning
• Solar Event Tracking with Deep Regression Networks: A Proof of Concept Evaluation
• Deep Complementary Joint Model for Complex Scene Registration and Few-shot Segmentation on Medical Images
• Panoptic One-Click Segmentation: Applied to Agricultural Data
• Cross-Modal Message Passing for Two-stream Fusion
• Deep Fusion Network for Image Completion
• Multimodal Transfer Learning-based Approaches for Retinal Vascular Segmentation
• MVStylizer: An Efficient Edge-Assisted Video Photorealistic Style Transfer System for Mobile Phones
• TriangleNet: Edge Prior Augmented Network for Semantic Segmentation through Cross-Task Consistency
• Semantic Segmentation of Radar Detections using Convolutions on Point Clouds
• Improved Predictive Deep Temporal Neural Networks with Trend Filtering
• Deep Learning Method for Cell-Wise Object Tracking, Velocity Estimation and Projection of Sensor Data over Time
• Short-Term Stock Price-Trend Prediction Using Meta-Learning
• Exploring the Effects of Data Augmentation for Drivable Area Segmentation
• FCN+RL: A Fully Convolutional Network followed by Refinement Layers to Offline Handwritten Signature Segmentation
• Discovering Latent Classes for Semi-Supervised Semantic Segmentation
• Gaussian Vector: An Efficient Solution for Facial Landmark Detection
• Learnable Histogram: Statistical Context Features for Deep Neural Networks
• Sketch In, Sketch Out: Accelerating both Learning and Inference for Structured Prediction with Kernels
• Importance-Aware Semantic Segmentation with Efficient Pyramidal Context Network for Navigational Assistant Systems
• Unsupervised Video Object Segmentation with Distractor-Aware Online Adaptation
• Can I teach a robot to replicate a line art
• Energy Consumption Analysis of pruned Semantic Segmentation Networks on an Embedded GPU
• Estimation of mitral valve hinge point coordinates -- deep neural net for echocardiogram segmentation
• Context Prior for Scene Segmentation
• Immunofluorescence Capillary Imaging Segmentation: Cases Study
• PØDA: Prompt-driven Zero-shot Domain Adaptation
• An Efficient Quantitative Approach for Optimizing Convolutional Neural Networks
• Detecting Invasive Ductal Carcinoma with Semi-Supervised Conditional GANs
• Cirrus: A Long-range Bi-pattern LiDAR Dataset
• Design Pseudo Ground Truth with Motion Cue for Unsupervised Video Object Segmentation
• On the Ability of a CNN to Realize Image-to-Image Language Conversion
• Spectrum-inspired Low-light Image Translation for Saliency Detection
• Diagnosing and exploiting the computational demands of videos games for deep reinforcement learning
• Depth-Adapted CNN for RGB-D cameras
• Background-Aware 3D Point Cloud Segmentationwith Dynamic Point Feature Aggregation
• Synthesizing Photorealistic Images with Deep Generative Learning
• CloudifierNet -- Deep Vision Models for Artificial Image Processing
• Deep Interactive Denoiser (DID) for X-Ray Computed Tomography
• LocaliseBot: Multi-view 3D object localisation with differentiable rendering for robot grasping