Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentation

Abstract

Spatial pyramid pooling module or encode-decoder structure are used in deep neural networks for semantic segmentation task. The former networks are able to encode multi-scale contextual information by probing the incoming features with filters or pooling operations at multiple rates and multiple effective fields-of-view, while the latter networks can capture sharper object boundaries by gradually recovering the spatial information. In this work, we propose to combine the advantages from both methods. Specifically, our proposed model, DeepLabv3+, extends DeepLabv3 by adding a simple yet effective decoder module to refine the segmentation results especially along object boundaries. We further explore the Xception model and apply the depthwise separable convolution to both Atrous Spatial Pyramid Pooling and decoder modules, resulting in a faster and stronger encoder-decoder network. We demonstrate the effectiveness of the proposed model on PASCAL VOC 2012 and Cityscapes datasets, achieving the test set performance of 89.0\% and 82.1\% without any post-processing. Our paper is accompanied with a publicly available reference implementation of the proposed models in Tensorflow at \url{https://github.com/tensorflow/models/tree/master/research/deeplab}.

ECCV 2018 camera ready

References in corpus (22)

• Distilling the Knowledge in a Neural Network
• MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications
• TensorFlow: Large-Scale Machine Learning on Heterogeneous Distributed Systems
• Rethinking Atrous Convolution for Semantic Image Segmentation
• Spatial Pyramid Pooling in Deep Convolutional Networks for Visual Recognition
• Efficient Inference in Fully Connected CRFs with Gaussian Edge Potentials
• DSSD : Deconvolutional Single Shot Detector
• ParseNet: Looking Wider to See Better
• The Cityscapes Dataset for Semantic Urban Scene Understanding
• Learning Deconvolution Network for Semantic Segmentation
• Stacked Hourglass Networks for Human Pose Estimation
• Deformable Convolutional Networks
• Beyond Skip Connections: Top-Down Modulation for Object Detection
• Fully Connected Deep Structured Networks
• Wider or Deeper: Revisiting the ResNet Model for Visual Recognition
• Flattened Convolutional Neural Networks for Feedforward Acceleration
• Semantic Image Segmentation via Deep Parsing Network
• Stacked Deconvolutional Network for Semantic Segmentation
• ExFuse: Enhancing Feature Fusion for Semantic Segmentation
• Fast Image Scanning with Deep Max-Pooling Convolutional Neural Networks
• Understanding Convolution for Semantic Segmentation
• Design of Efficient Convolutional Layers using Single Intra-channel Convolution, Topological Subdivisioning and Spatial "Bottleneck" Structure

Cited by in corpus (335)

• Multi-Task Learning for Dense Prediction Tasks: A Survey
• ABCNet: Attentive Bilateral Contextual Network for Efficient Semantic Segmentation of Fine-Resolution Remote Sensing Images
• A Novel Transformer Based Semantic Segmentation Scheme for Fine-Resolution Remote Sensing Images
• Rethinking Pre-training and Self-training
• MVSS-Net: Multi-View Multi-Scale Supervised Networks for Image Manipulation Detection
• Evolution of Image Segmentation using Deep Convolutional Neural Network: A Survey
• A2-FPN for Semantic Segmentation of Fine-Resolution Remotely Sensed Images
• Multi-Attention-Network for Semantic Segmentation of Fine Resolution Remote Sensing Images
• A Survey of End-to-End Driving: Architectures and Training Methods
• A2D2: Audi Autonomous Driving Dataset
• Deep Vessel Segmentation By Learning Graphical Connectivity
• Radar-Camera Fusion for Object Detection and Semantic Segmentation in Autonomous Driving: A Comprehensive Review
• Building extraction with vision transformer
• A Survey on Deep Learning-based Architectures for Semantic Segmentation on 2D images
• Bi-Temporal Semantic Reasoning for the Semantic Change Detection in HR Remote Sensing Images
• RTNet: Relation Transformer Network for Diabetic Retinopathy Multi-lesion Segmentation
• K-Net: Towards Unified Image Segmentation
• Deep Hough Transform for Semantic Line Detection
• DABNet: Depth-wise Asymmetric Bottleneck for Real-time Semantic Segmentation
• RGB-T Semantic Segmentation with Location, Activation, and Sharpening
• Global and Local Contrastive Self-Supervised Learning for Semantic Segmentation of HR Remote Sensing Images
• Looking Outside the Window: Wide-Context Transformer for the Semantic Segmentation of High-Resolution Remote Sensing Images
• The Fishyscapes Benchmark: Measuring Blind Spots in Semantic Segmentation
• Synscapes: A Photorealistic Synthetic Dataset for Street Scene Parsing
• A deep learning framework for quality assessment and restoration in video endoscopy
• Context-Aware Mixup for Domain Adaptive Semantic Segmentation
• Joint Spatio-Temporal Modeling for the Semantic Change Detection in Remote Sensing Images
• Masked-attention Mask Transformer for Universal Image Segmentation
• Context-Aware Interaction Network for RGB-T Semantic Segmentation
• SPG-Net: Segmentation Prediction and Guidance Network for Image Inpainting
• Shuffle Transformer: Rethinking Spatial Shuffle for Vision Transformer
• DDU-Net: Dual-Decoder-U-Net for Road Extraction Using High-Resolution Remote Sensing Images
• BDANet: Multiscale Convolutional Neural Network with Cross-directional Attention for Building Damage Assessment from Satellite Images
• 2018 Robotic Scene Segmentation Challenge
• Expectation-Maximization Attention Networks for Semantic Segmentation
• Light-Weight RefineNet for Real-Time Semantic Segmentation
• Hardware Acceleration of Sparse and Irregular Tensor Computations of ML Models: A Survey and Insights
• Dynamic Fusion Module Evolves Drivable Area and Road Anomaly Detection: A Benchmark and Algorithms
• Automated Evaluation of Semantic Segmentation Robustness for Autonomous Driving
• Universal Adversarial Examples in Remote Sensing: Methodology and Benchmark
• FocusNetv2: Imbalanced Large and Small Organ Segmentation with Adversarial Shape Constraint for Head and Neck CT Images
• Review of data analysis in vision inspection of power lines with an in-depth discussion of deep learning technology
• Large-scale Unsupervised Semantic Segmentation
• Uncertainty-aware Contrastive Distillation for Incremental Semantic Segmentation
• Deep Learning Techniques for In-Crop Weed Identification: A Review
• Learning Collision-Free Space Detection from Stereo Images: Homography Matrix Brings Better Data Augmentation
• RNGDet: Road Network Graph Detection by Transformer in Aerial Images
• SegGroup: Seg-Level Supervision for 3D Instance and Semantic Segmentation
• Building Extraction from Remote Sensing Images via an Uncertainty-Aware Network
• SuctionNet-1Billion: A Large-Scale Benchmark for Suction Grasping
• River Ice Segmentation with Deep Learning
• MudrockNet: Semantic Segmentation of Mudrock SEM Images through Deep Learning
• End-to-end Autonomous Driving with Semantic Depth Cloud Mapping and Multi-agent
• From SLAM to Situational Awareness: Challenges and Survey
• A Radar Signal Deinterleaving Method Based on Semantic Segmentation with Neural Network
• RoadFormer: Duplex Transformer for RGB-Normal Semantic Road Scene Parsing
• Adversarial Shape Learning for Building Extraction in VHR Remote Sensing Images
• Gaussian Dynamic Convolution for Efficient Single-Image Segmentation
• NFANet: A Novel Method for Weakly Supervised Water Extraction from High-Resolution Remote Sensing Imagery
• ExFuse: Enhancing Feature Fusion for Semantic Segmentation
• MP-ResNet: Multi-path Residual Network for the Semantic segmentation of High-Resolution PolSAR Images
• Panoptic Segmentation Meets Remote Sensing
• Grapy-ML: Graph Pyramid Mutual Learning for Cross-dataset Human Parsing
• Computer Vision on X-ray Data in Industrial Production and Security Applications: A Comprehensive Survey
• Fast and Accurate Road Crack Detection Based on Adaptive Cost-Sensitive Loss Function
• AIParsing: Anchor-free Instance-level Human Parsing
• Up or Down? Adaptive Rounding for Post-Training Quantization
• Progressive Glass Segmentation
• Behind the leaves -- Estimation of occluded grapevine berries with conditional generative adversarial networks
• Prior-aware Neural Network for Partially-Supervised Multi-Organ Segmentation
• CUTIE: Learning to Understand Documents with Convolutional Universal Text Information Extractor
• Global Aggregation then Local Distribution in Fully Convolutional Networks
• DAIS: Automatic Channel Pruning via Differentiable Annealing Indicator Search
• Decoupled Classification Refinement: Hard False Positive Suppression for Object Detection
• Deep Multi-Branch Aggregation Network for Real-Time Semantic Segmentation in Street Scenes
• FoodSAM: Any Food Segmentation
• Strip Pooling: Rethinking Spatial Pooling for Scene Parsing
• Attention-guided Chained Context Aggregation for Semantic Segmentation
• METER: a mobile vision transformer architecture for monocular depth estimation
• Domain Adaptation for Semantic Segmentation with Maximum Squares Loss
• HAFormer: Unleashing the Power of Hierarchy-Aware Features for Lightweight Semantic Segmentation
• Real-Time Human Pose Estimation on a Smart Walker using Convolutional Neural Networks
• S${}^3$M-Net: Joint Learning of Semantic Segmentation and Stereo Matching for Autonomous Driving
• MMSFormer: Multimodal Transformer for Material and Semantic Segmentation
• Road Extraction with Satellite Images and Partial Road Maps
• Unveiling Energy Efficiency in Deep Learning: Measurement, Prediction, and Scoring across Edge Devices
• CD-CTFM: A Lightweight CNN-Transformer Network for Remote Sensing Cloud Detection Fusing Multiscale Features
• Revisiting Contrastive Methods for Unsupervised Learning of Visual Representations
• Dual Branch Neural Network for Sea Fog Detection in Geostationary Ocean Color Imager
• Towards Better Accuracy-efficiency Trade-offs: Divide and Co-training
• Deep Co-supervision and Attention Fusion Strategy for Automatic COVID-19 Lung Infection Segmentation on CT Images
• Pseudo-LiDAR Based Road Detection
• A Self-Distillation Embedded Supervised Affinity Attention Model for Few-Shot Segmentation
• Rethinking Domain Generalization: Discriminability and Generalizability
• SBSS: Stacking-Based Semantic Segmentation Framework for Very High Resolution Remote Sensing Image
• AlphaGAN: Generative adversarial networks for natural image matting
• Point Label Aware Superpixels for Multi-species Segmentation of Underwater Imagery
• Pixel-Anchor: A Fast Oriented Scene Text Detector with Combined Networks
• Semi-Supervised Building Footprint Generation with Feature and Output Consistency Training
• Mobile-Seed: Joint Semantic Segmentation and Boundary Detection for Mobile Robots
• ModaNet: A Large-Scale Street Fashion Dataset with Polygon Annotations
• Hidden Path Selection Network for Semantic Segmentation of Remote Sensing Images
• A recurrent CNN for online object detection on raw radar frames
• Domain Generalization Using a Mixture of Multiple Latent Domains
• Birds of A Feather Flock Together: Category-Divergence Guidance for Domain Adaptive Segmentation
• PIP-Net: Pedestrian Intention Prediction in the Wild
• Adversarial Attacks on Video Object Segmentation with Hard Region Discovery
• Segmentation of Skin Lesions and their Attributes Using Multi-Scale Convolutional Neural Networks and Domain Specific Augmentations
• External Attention Assisted Multi-Phase Splenic Vascular Injury Segmentation with Limited Data
• SemiCurv: Semi-Supervised Curvilinear Structure Segmentation
• End-To-End Optimization of LiDAR Beam Configuration for 3D Object Detection and Localization
• Macroscale fracture surface segmentation via semi-supervised learning considering the structural similarity
• Delving Deeper into Anti-aliasing in ConvNets
• Learning Densities in Feature Space for Reliable Segmentation of Indoor Scenes
• Knowledge Adaptation for Efficient Semantic Segmentation
• ExtremeC3Net: Extreme Lightweight Portrait Segmentation Networks using Advanced C3-modules
• Joint Semantic Segmentation and Boundary Detection using Iterative Pyramid Contexts
• Deep Unfolding Multi-modal Image Fusion Network via Attribution Analysis
• ILabel: Interactive Neural Scene Labelling
• Scribble Hides Class: Promoting Scribble-Based Weakly-Supervised Semantic Segmentation with Its Class Label
• Spatially-Adaptive Filter Units for Compact and Efficient Deep Neural Networks
• Multitask Learning for Scalable and Dense Multilayer Bayesian Map Inference
• LookinGood: Enhancing Performance Capture with Real-time Neural Re-Rendering
• Category-Association Based Similarity Matching for Novel Object Pick-and-Place Task
• CFPNet-M: A Light-Weight Encoder-Decoder Based Network for Multimodal Biomedical Image Real-Time Segmentation
• LSENet: Location and Seasonality Enhanced Network for Multi-Class Ocean Front Detection
• Efficient few-shot learning for pixel-precise handwritten document layout analysis
• Learning at a Glance: Towards Interpretable Data-limited Continual Semantic Segmentation via Semantic-Invariance Modelling
• Enhancing Environmental Enforcement with Near Real-Time Monitoring: Likelihood-Based Detection of Structural Expansion of Intensive Livestock Farms
• Boosting Visual Recognition in Real-world Degradations via Unsupervised Feature Enhancement Module with Deep Channel Prior
• RCNet: Deep Recurrent Collaborative Network for Multi-View Low-Light Image Enhancement
• Efficient Segmentation: Learning Downsampling Near Semantic Boundaries
• SAN: Scale-Aware Network for Semantic Segmentation of High-Resolution Aerial Images
• ACE: Adapting to Changing Environments for Semantic Segmentation
• Multi-Target Domain Adaptation with Collaborative Consistency Learning
• LiDARNet: A Boundary-Aware Domain Adaptation Model for Point Cloud Semantic Segmentation
• DSNet for Real-Time Driving Scene Semantic Segmentation
• JSNet: Joint Instance and Semantic Segmentation of 3D Point Clouds
• Fully Convolutional Networks for Panoptic Segmentation
• A deep learning-based framework for segmenting invisible clinical target volumes with estimated uncertainties for post-operative prostate cancer radiotherapy
• Customizable Architecture Search for Semantic Segmentation
• Semantic Correlation Promoted Shape-Variant Context for Segmentation
• SEnSeI: A Deep Learning Module for Creating Sensor Independent Cloud Masks
• Context-Aware Image Matting for Simultaneous Foreground and Alpha Estimation
• Real-Time High-Resolution Background Matting
• HS3-Bench: A Benchmark and Strong Baseline for Hyperspectral Semantic Segmentation in Driving Scenarios
• Conditional Driving from Natural Language Instructions
• SegSort: Segmentation by Discriminative Sorting of Segments
• ShareCMP: Polarization-Aware RGB-P Semantic Segmentation
• Robust Representation Learning with Feedback for Single Image Deraining
• Comprehensive Multi-Modal Interactions for Referring Image Segmentation
• Temporally Distributed Networks for Fast Video Semantic Segmentation
• IrisNet: Deep Learning for Automatic and Real-time Tongue Contour Tracking in Ultrasound Video Data using Peripheral Vision
• Enhancing Cross-task Black-Box Transferability of Adversarial Examples with Dispersion Reduction
• Real-time Fusion Network for RGB-D Semantic Segmentation Incorporating Unexpected Obstacle Detection for Road-driving Images
• Hierarchical Human Parsing with Typed Part-Relation Reasoning
• HisynSeg: Weakly-Supervised Histopathological Image Segmentation via Image-Mixing Synthesis and Consistency Regularization
• RFTrans: Leveraging Refractive Flow of Transparent Objects for Surface Normal Estimation and Manipulation
• Tree-structured Kronecker Convolutional Network for Semantic Segmentation
• AMD-HookNet for Glacier Front Segmentation
• Zero-Shot Semantic Segmentation
• Sparse Semantic Map-Based Monocular Localization in Traffic Scenes Using Learned 2D-3D Point-Line Correspondences
• Semi-supervised Domain Adaptation based on Dual-level Domain Mixing for Semantic Segmentation
• Compact Global Descriptor for Neural Networks
• Spectral Pyramid Graph Attention Network for Hyperspectral Image Classification
• PointFlow: Flowing Semantics Through Points for Aerial Image Segmentation
• BoundarySqueeze: Image Segmentation as Boundary Squeezing
• Scene Gated Social Graph: Pedestrian Trajectory Prediction Based on Dynamic Social Graphs and Scene Constraints
• Learning a Joint Embedding of Multiple Satellite Sensors: A Case Study for Lake Ice Monitoring
• WaveSNet: Wavelet Integrated Deep Networks for Image Segmentation
• Can we cover navigational perception needs of the visually impaired by panoptic segmentation?
• DCL: Differential Contrastive Learning for Geometry-Aware Depth Synthesis
• High-resolution semantically-consistent image-to-image translation
• Segmenting Known Objects and Unseen Unknowns without Prior Knowledge
• Pixel Level Data Augmentation for Semantic Image Segmentation using Generative Adversarial Networks
• ST-MTL: Spatio-Temporal Multitask Learning Model to Predict Scanpath While Tracking Instruments in Robotic Surgery
• Global and Local Features through Gaussian Mixture Models on Image Semantic Segmentation
• Deep Convolutional Neural Networks with Spatial Regularization, Volume and Star-shape Priori for Image Segmentation
• Learning Compositional Neural Information Fusion for Human Parsing
• Multi-Level Label Correction by Distilling Proximate Patterns for Semi-supervised Semantic Segmentation
• Deep Common Feature Mining for Efficient Video Semantic Segmentation
• OSDMamba: Enhancing Oil Spill Detection from Remote Sensing Images Using Selective State Space Model
• DDNet: Cartesian-polar Dual-domain Network for the Joint Optic Disc and Cup Segmentation
• PFENet++: Boosting Few-shot Semantic Segmentation with the Noise-filtered Context-aware Prior Mask
• Robust Semantic Segmentation with Superpixel-Mix
• E${}^2$Net: An Edge Enhanced Network for Accurate Liver and Tumor Segmentation on CT Scans
• Analysis on DeepLabV3+ Performance for Automatic Steel Defects Detection
• CARLA2Real: a tool for reducing the sim2real appearance gap in CARLA simulator
• Spatial-Temporal Map Vehicle Trajectory Detection Using Dynamic Mode Decomposition and Res-UNet+ Neural Networks
• BRULÈ: Barycenter-Regularized Unsupervised Landmark Extraction
• Retinal OCT Synthesis with Denoising Diffusion Probabilistic Models for Layer Segmentation
• CNN Acceleration by Low-rank Approximation with Quantized Factors
• Structure-guided Diffusion Transformer for Low-Light Image Enhancement
• Phase-aggregated Dual-branch Network for Efficient Fingerprint Dense Registration
• View it like a radiologist: Shifted windows for deep learning augmentation of CT images
• Syn-Mediverse: A Multimodal Synthetic Dataset for Intelligent Scene Understanding of Healthcare Facilities
• Road detection via a dual-task network based on cross-layer graph fusion modules
• Improving Road Segmentation in Challenging Domains Using Similar Place Priors
• Crack Detection as a Weakly-Supervised Problem: Towards Achieving Less Annotation-Intensive Crack Detectors
• ObjectAug: Object-level Data Augmentation for Semantic Image Segmentation
• Differentiable Multi-Granularity Human Representation Learning for Instance-Aware Human Semantic Parsing
• Unsupervised domain adaptation via coarse-to-fine feature alignment method using contrastive learning
• Unifying Neural Learning and Symbolic Reasoning for Spinal Medical Report Generation
• Query by Semantic Sketch
• DISIR: Deep Image Segmentation with Interactive Refinement
• Semi-supervised Skin Detection by Network with Mutual Guidance
• DAPAS : Denoising Autoencoder to Prevent Adversarial attack in Semantic Segmentation
• BusyHands: A Hand-Tool Interaction Database for Assembly Tasks Semantic Segmentation
• Sketch2code: Generating a website from a paper mockup
• Improving Semantic Segmentation via Dilated Affinity
• Making a Case for 3D Convolutions for Object Segmentation in Videos
• Mapping Informal Settlements in Developing Countries with Multi-resolution, Multi-spectral Data
• EfficientHRNet: Efficient Scaling for Lightweight High-Resolution Multi-Person Pose Estimation
• Inductive Guided Filter: Real-time Deep Image Matting with Weakly Annotated Masks on Mobile Devices
• m-RevNet: Deep Reversible Neural Networks with Momentum
• Gradient Information Guided Deraining with A Novel Network and Adversarial Training
• IDD: A Dataset for Exploring Problems of Autonomous Navigation in Unconstrained Environments
• SS3D: Single Shot 3D Object Detector
• Magnifier: A Multi-grained Neural Network-based Architecture for Burned Area Delineation
• WasteGAN: Data Augmentation for Robotic Waste Sorting through Generative Adversarial Networks
• Seg-LSTM: Performance of xLSTM for Semantic Segmentation of Remotely Sensed Images
• Contextual Guided Segmentation Framework for Semi-supervised Video Instance Segmentation
• Boosted GAN with Semantically Interpretable Information for Image Inpainting
• SRMF: A Data Augmentation and Multimodal Fusion Approach for Long-Tail UHR Satellite Image Segmentation
• Learning Ordinality in Semantic Segmentation
• Learning Semantic Neural Tree for Human Parsing
• Learn to Segment Retinal Lesions and Beyond
• FaceShapeGene: A Disentangled Shape Representation for Flexible Face Image Editing
• How to Relieve Distribution Shifts in Semantic Segmentation for Off-Road Environments
• AIO-P: Expanding Neural Performance Predictors Beyond Image Classification
• OrthoSeg: A Deep Multimodal Convolutional Neural Network for Semantic Segmentation of Orthoimagery
• Panoptic One-Click Segmentation: Applied to Agricultural Data
• Direct Regression of Distortion Field from a Single Fingerprint Image
• Deep Dual Pyramid Network for Barcode Segmentation using Barcode-30k Database
• Automated Charge Transition Detection in Quantum Dot Charge Stability Diagrams
• Boosting Image Outpainting with Semantic Layout Prediction
• Dilated Convolutions with Lateral Inhibitions for Semantic Image Segmentation
• FrostNet: Towards Quantization-Aware Network Architecture Search
• Gland Segmentation Via Dual Encoders and Boundary-Enhanced Attention
• Improving the Resolution of CNN Feature Maps Efficiently with Multisampling
• Rainy screens: Collecting rainy datasets, indoors
• GANtruth - an unpaired image-to-image translation method for driving scenarios
• Deep Consensus Learning
• YUVMultiNet: Real-time YUV multi-task CNN for autonomous driving
• Parsing R-CNN for Instance-Level Human Analysis
• Understanding Pixel-level 2D Image Semantics with 3D Keypoint Knowledge Engine
• The Application of Deep Learning for Lymph Node Segmentation: A Systematic Review
• Feature-Fused Context-Encoding Network for Neuroanatomy Segmentation
• Application of Computer Vision and Machine Learning for Digitized Herbarium Specimens: A Systematic Literature Review
• Interpretable Neural Network Decoupling
• Domain Generalization for Endoscopic Image Segmentation by Disentangling Style-Content Information and SuperPixel Consistency
• ClimateGAN: Raising Climate Change Awareness by Generating Images of Floods
• SSL4SAR: Self-Supervised Learning for Glacier Calving Front Extraction from SAR Imagery
• Impact of LiDAR visualisations on semantic segmentation of archaeological objects
• Dynamic Hierarchical Mimicking Towards Consistent Optimization Objectives
• Defective samples simulation through Neural Style Transfer for automatic surface defect segment
• Exploring the Effects of Data Augmentation for Drivable Area Segmentation
• Echocardiography Segmentation with Enforced Temporal Consistency
• Correlating Edge, Pose with Parsing
• Real-time Human Finger Pointing Recognition and Estimation for Robot Directives Using a Single Web-Camera
• Transferring and Regularizing Prediction for Semantic Segmentation
• Learning Navigation Costs from Demonstration with Semantic Observations
• Importance of Self-Consistency in Active Learning for Semantic Segmentation
• Towards Investigating Residual Hearing Loss: Quantification of Fibrosis in a Novel Cochlear OCT Dataset
• PT-ResNet: Perspective Transformation-Based Residual Network for Semantic Road Image Segmentation
• High Frequency Residual Learning for Multi-Scale Image Classification
• Adaptive Temporal Encoding Network for Video Instance-level Human Parsing
• Spatio-temporal Video Re-localization by Warp LSTM
• Towards Object Segmentation Mask Selection Using Specular Reflections
• Semantic Segmentation and Object Detection Towards Instance Segmentation: Breast Tumor Identification
• Reducing the feature divergence of RGB and near-infrared images using Switchable Normalization
• Framework-agnostic Semantically-aware Global Reasoning for Segmentation
• Detection and Prediction of Nutrient Deficiency Stress using Longitudinal Aerial Imagery
• Multi Receptive Field Network for Semantic Segmentation
• A Macro-Micro Weakly-supervised Framework for AS-OCT Tissue Segmentation
• Using a Supervised Method without supervision for foreground segmentation
• S2cGAN: Semi-Supervised Training of Conditional GANs with Fewer Labels
• ASC: Adaptive Scale Feature Map Compression for Deep Neural Network
• Real-Time Semantic Segmentation via Auto Depth, Downsampling Joint Decision and Feature Aggregation
• Boundary Guidance Hierarchical Network for Real-Time Tongue Segmentation
• C-DLinkNet: considering multi-level semantic features for human parsing
• Seismic horizon detection with neural networks
• Multi-Scale Grouped Prototypes for Interpretable Semantic Segmentation
• Don't ignore Dropout in Fully Convolutional Networks
• RRNet: Repetition-Reduction Network for Energy Efficient Decoder of Depth Estimation
• Hyperspectral vs. RGB for Pedestrian Segmentation in Urban Driving Scenes: A Comparative Study
• SegAssess: Panoramic quality mapping for robust and transferable unsupervised segmentation assessment
• Inserting Videos into Videos
• The Ethical Dilemma when (not) Setting up Cost-based Decision Rules in Semantic Segmentation
• Multi-scale Cross-form Pyramid Network for Stereo Matching
• Improving Annotation for 3D Pose Dataset of Fine-Grained Object Categories
• Diagnostics in Semantic Segmentation
• Multiple Myeloma Cancer Cell Instance Segmentation
• Dense Prediction with Attentive Feature Aggregation
• Bounding Box Embedding for Single Shot Person Instance Segmentation
• Contour Flow Constraint: Preserving Global Shape Similarity for Deep Learning based Image Segmentation
• DASNet: Reducing Pixel-level Annotations for Instance and Semantic Segmentation
• Learning Propagation for Arbitrarily-structured Data
• Automated Segmentation of Brain Gray Matter Nuclei on Quantitative Susceptibility Mapping Using Deep Convolutional Neural Network
• Lightweight U-Net for High-Resolution Breast Imaging
• A Study on Trees's Knots Prediction from their Bark Outer-Shape
• A De-raining semantic segmentation network for real-time foreground segmentation
• A Survey On 3D Inner Structure Prediction from its Outer Shape
• Rethinking Fully Convolutional Networks for the Analysis of Photoluminescence Wafer Images
• Learning Deep Multimodal Feature Representation with Asymmetric Multi-layer Fusion
• Robust Semantic Segmentation By Dense Fusion Network On Blurred VHR Remote Sensing Images
• MOSE: Monocular Semantic Reconstruction Using NeRF-Lifted Noisy Priors
• Generating Data Augmentation samples for Semantic Segmentation of Salt Bodies in a Synthetic Seismic Image Dataset
• RethNet: Object-by-Object Learning for Detecting Facial Skin Problems
• A Parametric Top-View Representation of Complex Road Scenes
• Localized Interactive Instance Segmentation
• How to Train Neural Networks for Flare Removal
• Beyond Single Stage Encoder-Decoder Networks: Deep Decoders for Semantic Image Segmentation
• Understanding Road Layout from Videos as a Whole
• NoPeopleAllowed: The Three-Step Approach to Weakly Supervised Semantic Segmentation
• Rethinking Lightweight Convolutional Neural Networks for Efficient and High-quality Pavement Crack Detection
• Combining Supervised and Un-supervised Learning for Automatic Citrus Segmentation
• Efficient Prediction of Dense Visual Embeddings via Distillation and RGB-D Transformers
• Beyond Blur: A Semantic Tri-view Pipeline for Teledermatology Gradability via Skin Micro-relief
• Weakly supervised training of pixel resolution segmentation models on whole slide images
• 3rd Place Solution for Short-video Face Parsing Challenge
• Compact retail shelf segmentation for mobile deployment
• An Abstraction Model for Semantic Segmentation Algorithms
• A Point-Neighborhood Learning Framework for Nasal Endoscope Image Segmentation
• Take a NAP: Non-Autoregressive Prediction for Pedestrian Trajectories
• Recommendation or Discrimination?: Quantifying Distribution Parity in Information Retrieval Systems
• Multilayer Dense Connections for Hierarchical Concept Classification
• DV3+HED+: A DCNNs-based Framework to Monitor Temporary Works and ESAs in Railway Construction Project Using VHR Satellite Images
• One-Shot Object Affordance Detection in the Wild
• Semantic Segmentation for Urban-Scene Images
• SeismiQB -- a novel framework for deep learning with seismic data
• Innovative Quantitative Analysis for Disease Progression Assessment in Familial Cerebral Cavernous Malformations
• A Distraction Score for Watermarks
• ELKPPNet: An Edge-aware Neural Network with Large Kernel Pyramid Pooling for Learning Discriminative Features in Semantic Segmentation
• CNN-based Semantic Segmentation using Level Set Loss