Ecosyste.ms: Awesome

An open API service indexing awesome lists of open source software.
Awesome Lists | Featured Topics | Projects
https://github.com/shawnyuen/semantic_seg_paper_collection

convolutional-networks deep-learning fully-convolutional-networks image-segmentation instance-segmentation interactive-segmentation machine-learning neural-networks object-segmentation panoptic-segmentation promptable-segmentation semantic-segmentation video-segmentation
Last synced: 11 days ago
JSON representation
Host: GitHub
URL: https://github.com/shawnyuen/semantic_seg_paper_collection
Owner: shawnyuen
Created: 2017-03-12T02:36:22.000Z (over 7 years ago)
Default Branch: master
Last Pushed: 2023-06-19T14:38:13.000Z (over 1 year ago)
Last Synced: 2024-05-21T02:24:44.273Z (6 months ago)
Topics: convolutional-networks, deep-learning, fully-convolutional-networks, image-segmentation, instance-segmentation, interactive-segmentation, machine-learning, neural-networks, object-segmentation, panoptic-segmentation, promptable-segmentation, semantic-segmentation, video-segmentation
Homepage:
Size: 604 KB
Stars: 128
Watchers: 17
Forks: 23
Open Issues: 0
Metadata Files:
- Readme: README.md
Awesome Lists containing this project

awesome-computer-vision-papers - SemanticSegPaperCollection
README

        # semantic_seg_paper_collection

## Survey or Review

### A Review on Deep Learning Techniques Applied to Semantic Segmentation arXiv 2017 [[paper]](https://arxiv.org/abs/1704.06857)

### Survey of Recent Progress in Semantic Image Segmentation with CNNs SCIS 2018 [[paper]](https://link.springer.com/article/10.1007/s11432-017-9189-6)

### Survey on Semantic Segmentation Using Deep Learning Techniques Neurocomputing 2019 [[paper]](https://www.sciencedirect.com/science/article/pii/S092523121930181X)

### Understanding Deep Learning Techniques for Image Segmentation arXiv 2019 [[paper]](https://arxiv.org/abs/1907.06119)

### Methods and Datasets on Semantic Segmentation A Review Neurocomputing 2018 [[paper]](https://www.sciencedirect.com/science/article/pii/S0925231218304077)

### A Review of Semantic Segmentation Using Deep Neural Networks IJMIR 2019 [[paper]](https://link.springer.com/article/10.1007/s13735-017-0141-z)

### Deep Semantic Segmentation of Natural and Medical Images A Review arXiv 2019 [[paper]](https://arxiv.org/abs/1910.07655)

### Evolution of Image Segmentation using Deep Convolutional Neural Network A Survey arXiv 2020 [[paper]](https://arxiv.org/abs/2001.04074)

### Image Segmentation Using Deep Learning A Survey arXiv 2020 [[paper]](https://arxiv.org/abs/2001.05566)

### Unsupervised Domain Adaptation in Semantic Segmentation a Review arXiv 2020 [[paper]](https://arxiv.org/abs/2005.10876)

### A Survey of Loss Functions for Semantic Segmentation arXiv 2020 [[paper]](https://arxiv.org/abs/2006.14822) [[code]](https://github.com/shruti-jadon/Semantic-Segmentation-Loss-Functions)

### A Survey on Instance Segmentation State of the Art arXiv 2020 [[paper]](https://arxiv.org/abs/2007.00047)

### Transformer-Based Visual Segmentation - A Survey arXiv 2023 [[paper]](https://arxiv.org/abs/2304.09854)

### Semantic Segmentation Using Vision Transformers - A Survey arXiv 2023 [[paper]](https://arxiv.org/abs/2305.03273)

## Dataset

### (VOC) The Pascal Visual Object Classes (VOC) Challenge IJCV 2010 [[paper]](https://link.springer.com/article/10.1007/s11263-009-0275-4)

### (MS COCO) Microsoft COCO Common Objects in Context ECCV 2014 [[paper]](https://rd.springer.com/chapter/10.1007/978-3-319-10602-1_48)

### (Cityscapes) The Cityscapes Dataset for Semantic Urban Scene Understanding CVPR 2016 [[paper]](http://www.cv-foundation.org/openaccess/content_cvpr_2016/html/Cordts_The_Cityscapes_Dataset_CVPR_2016_paper.html)

### (ADE20K) Scene Parsing through ADE20K Dataset CVPR 2017 [[paper]](http://openaccess.thecvf.com/content_cvpr_2017/html/Zhou_Scene_Parsing_Through_CVPR_2017_paper.html) [[arXiv paper]](https://arxiv.org/abs/1608.05442)

## 2023

### Boosting Semantic Segmentation with Semantic Boundaries arXiv 2023 [[paper]](https://arxiv.org/abs/2304.09427)

### Coupling Global Context and Local Contents for Weakly-Supervised Semantic Segmentation arXiv 2023 [[paper]](https://arxiv.org/abs/2304.09059)

### Deep Hierarchical Semantic Segmentation CVPR 2023 [[paper]](https://arxiv.org/abs/2203.14335) [[code]](https://github.com/lingorX/HieraSeg)

### FCN+ - Global Receptive Convolution Makes FCN Great Again arXiv 2023 [[paper]](https://arxiv.org/abs/2303.04589)

"Global receptive convolution, GRC", "PASCAL VOC 2012: 79.42 mIoU", "Cityscapes: 80.53 mIoU", "ADE20K: 45.74 mIoU"

### HFGD - High-level Feature Guided Decoder for Semantic Segmentation arXiv 2023 [[paper]](https://arxiv.org/abs/2303.08646)

"Cityscapes: 83.1 mIoU using single scale and os=4", "Cityscapes: 83.2 mIoU using single scale and os=2", "Cityscapes: 83.8 mIoU using multi-scale and os=4", "Cityscapes: 84.0 mIoU using multi-scale and os=2", "COCOStuff164K: 49.0 mIoU using single scale and os=4", "COCOStuff164K: 49.4 mIoU using multi-scale and os=4", "Pascal Context: 63.8 mIoU using single scale and os=4", "Pascal Context: 64.9 mIoU using multi-scale and os=4"

### MED-VT - Multiscale Encoder-Decoder Video Transformer with Application to Object Segmentation CVPR 2023 [[paper]](https://arxiv.org/abs/2304.05930)

### OVeNet - Offset Vector Network for Semantic Segmentation arXiv 2023 [[paper]](https://arxiv.org/abs/2303.14516)

"improving class predictions by learning to selectively exploit information from neighboring pixels"

### Reliability-Hierarchical Memory Network for Scribble-Supervised Video Object Segmentation arXiv 2023 [[paper]](https://arxiv.org/abs/2303.14384)

"so-so"

### Segment Anything arXiv 2023 [[paper]](https://arxiv.org/abs/2304.02643)

"milestone", "promptable segmentation", "segment anything model, sam"

## 2022

### Global Spectral Filter Memory Network ECCV 2022 [[paper]](https://arxiv.org/abs/2210.05567) [[code]](https://github.com/workforai/GSFM)

### (Mask2Former) Masked-attention Mask Transformer for Universal Image Segmentation CVPR 2022 [[arXiv paper]](https://arxiv.org/abs/2112.01527) [[code]](https://github.com/facebookresearch/Mask2Former)

### RepParser End-to-End Multiple Human Parsing with Representative Parts arXiv 2022 [[paper]](https://arxiv.org/abs/2208.12908)

## 2021

### A Simple Baseline for Semi-supervised Semantic Segmentation with Strong Data Augmentation arXiv 2021 [[paper]](https://arxiv.org/abs/2104.07256)

### A Unified Efficient Pyramid Transformer for Semantic Segmentation arXiv 2021 [[paper]](https://arxiv.org/abs/2107.14209)

### Active Boundary Loss for Semantic Segmentation arXiv 2021 [[paper]](https://arxiv.org/abs/2102.02696)

### AttaNet Attention-Augmented Network for Fast and Accurate Scene Parsing AAAI 2021

### BiSeNet V2 - Bilateral Network with Guided Aggregation for Real-time Semantic Segmentation IJCV 2020 [[ijcv paper]](https://link.springer.com/article/10.1007/s11263-021-01515-2)  [[arXiv paper]]https://arxiv.org/abs/2004.02147)

"Real-time"

### Exploring Cross-image Pixel Contrast for Semantic Segmentation arXiv 2021 [[paper]](https://arxiv.org/abs/2101.11939)

### Learning Statistical Texture for Semantic Segmentation arXiv 2021 [[paper]](https://arxiv.org/abs/2103.04133)

"ADE20K validation set: 46.48 mIoU", "PASCAL Context validation set: 55.8 mIoU", "Cityscapes test set: 82.3 mIoU"

### Mining Contextual Information Beyond Image for Semantic Segmentation ICCV 2021 [[paper]](https://openaccess.thecvf.com/content/ICCV2021/html/Jin_Mining_Contextual_Information_Beyond_Image_for_Semantic_Segmentation_ICCV_2021_paper.html) [[arXiv paper]](https://arxiv.org/abs/2108.11819)

### Per-Pixel Classification is Not All You Need for Semantic Segmentation arXiv 2021 [[paper]](https://arxiv.org/abs/2107.06278) [[code]](https://github.com/facebookresearch/MaskFormer)

"ADE20K validation set: 46.0 mIoU (single-scale, ConvNet backbones)", "ADE20K validation set: 48.1 mIoU (multi-scale, ConvNet backbones)", "ADE20K validation set: 54.1 mIoU (single-scale, Transformer backbones)", "ADE20K validation set: 55.6.0 mIoU (multi-scale, Transformer backbones)", 

### Pyramid Vision Transformer A Versatile Backbone for Dense Prediction without Convolutions arXiv [[paper]](https://export.arxiv.org/abs/2102.12122)

### Rethinking Semantic Segmentation from a Sequence-to-Sequence Perspective with Transformers CVPR 2021 [[paper]](https://arxiv.org/abs/2012.15840) [[code]](https://github.com/fudan-zvg/SETR)

### SegFormer Simple and Efficient Design for Semantic Segmentation with Transformers arXiv 2021 [[paper]](https://arxiv.org/abs/2105.15203)

"Cityscapes test set: 82.2 mIoU with ImageNet-1K pre-training", "Cityscapes test set: 83.1 mIoU with ImageNet-1K pre-training and Mapillary pre-training"

### Segmenter Transformer for Semantic Segmentation arXiv 2021 [[paper]](https://arxiv.org/abs/2105.05633)

"ADE20K validation set: 50.77 mIoU", "PASCAL Context validation set: 55.6 mIoU", "Cityscapes validation set: 80.7 mIoU"

## 2020

### A Holistically-guided Decoder for Deep Representation Learning with Applications to Semantic Segmentation and Object Detection arXiv 2020 [[paper]]()

### Auto Seg-Loss Searching Metric Surrogates for Semantic Segmentation arXiv 2020 [[paper]](https://arxiv.org/abs/2010.07930)

### Auto-Panoptic Cooperative Multi-Component Architecture Search for Panoptic Segmentation NIPS 2020 [[paper]](https://arxiv.org/abs/2010.16119) [[code]](https://github.com/Jacobew/AutoPanoptic)

### Beyond Single Stage Encoder-Decoder Networks: Deep Decoders for Semantic Image Segmentation arXiv 2020 [[paper]](https://arxiv.org/abs/2007.09746)

### BlendMask Top-Down Meets Bottom-Up for Instance Segmentation arXiv 2020 [[paper]](https://arxiv.org/abs/2001.00309)

### Boundary-preserving Mask R-CNN ECCV 2020 [[paper]](https://arxiv.org/abs/2007.08921) [[code]](https://github.com/hustvl/BMaskR-CNN)

### Classes Matter A Fine-grained Adversarial Approach to Cross-domain Semantic Segmentation ECCV 2020 [[paper]](https://arxiv.org/abs/2007.09222)

### Context Prior for Scene Segmentation arXiv 2020 [[paper]](https://arxiv.org/abs/2004.01547)

### Deep Convolutional Neural Networks with Spatial Regularization, Volume and Star-shape Priori for Image Segmentation arXiv 2020 [[paper]](https://arxiv.org/abs/2002.03989)

### Disentangled Non-Local Neural Networks ECCV 2020 [[arXiv paper]](https://arxiv.org/abs/2006.06668) [[SemanticSeg code]](https://github.com/yinmh17/DNL-Semantic-Segmentation) [[ObjectDetect code]](https://github.com/Howal/DNL-Object-Detection)

### EfficientFCN Holistically-guided Decoding for Semantic Segmentation ECCV 2020 [[paper]]()

### EfficientSeg An Efficient Semantic Segmentation Network arXiv 2020 [[paper]](https://arxiv.org/abs/2009.06469)

### FasterSeg Searching for Faster Real-time Semantic Segmentation ICLR 2020 [[paper]](https://arxiv.org/abs/1912.10917) [[code]](https://github.com/TAMU-VITA/FasterSeg)

### Fully Convolutional Networks for Panoptic Segmentation arXiv 2020

### Hierarchical Multi-Scale Attention for Semantic Segmentation arXiv 2020 [[paper]](https://arxiv.org/abs/2005.10821)

"on Cityscapes test set, Hierarchical Multi-Scale Attention gets mIoU 85.4%.", "on Mapillary validation set, it gets mIoU 61.1%."

### HigherHRNet Scale-aware Representation Learning for Bottom-Up Human Pose Estimation CVPR 2020 [[paper]](https://arxiv.org/abs/1908.10357)

"Bottom-up Higher-Resolution Networks for Multi-Person Pose Estimation"

### Improving Semantic Segmentation via Decoupled Body and Edge Supervision ECCV 2020 [[paper]](https://arxiv.org/abs/2007.10035)

### Interactive Object Segmentation with Inside-Outside Guidance CVPR 2020 [[paper]](http://openaccess.thecvf.com/content_CVPR_2020/html/Zhang_Interactive_Object_Segmentation_With_Inside-Outside_Guidance_CVPR_2020_paper.html)

### (Naive-Student) Leveraging Semi-Supervised Learning in Video Sequences for Urban Scene Segmentation arXiv 2020 [[paper]](https://arxiv.org/abs/2005.10266)

"on Cityscapes test-fine set, Navie-Student gets mIoU 85.2%."

### MaX-DeepLab End-to-End Panoptic Segmentation with Mask Transformers arXiv 2020 [[paper]]()

### Learning Dynamic Routing for Semantic Segmentation CVPR 2020 [[paper]](https://openaccess.thecvf.com/content_CVPR_2020/html/Li_Learning_Dynamic_Routing_for_Semantic_Segmentation_CVPR_2020_paper.html) [[arXiv paper]](https://arxiv.org/abs/2003.10401)

### Panoptic-DeepLab A Simple Strong and Fast Baseline for Bottom-Up Panoptic Segmentation CVPR 2020 [[paper]](https://arxiv.org/abs/1911.10194)

### PseudoSeg Designing Pseudo Labels for Semantic Segmentation arXiv 2020 [[paper]]()

### Scaling Wide Residual Networks for Panoptic Segmentation arXiv 2020 [[paper]]()

### SegBlocks Block-based Dynamic Resolution Networks for Real-time Segmentation arXiv 2020 [[paper]]()

### SegFix Model-Agnostic Boundary Refinement for Segmentation ECCV 2020 [[paper]](https://arxiv.org/abs/2007.04269) [[code]](https://github.com/openseg-group/openseg.pytorch)

### Simple Copy-Paste is a Strong Data Augmentation Method for Instance Segmentation arXiv 2020 [[paper]]()

### The Devil is in the Boundary Exploiting Boundary Representation for Basis-based Instance Segmentation arXiv 2020 [[paper]](https://arxiv.org/abs/2011.13241)

### Unifying Training and Inference for Panoptic Segmentation CVPR 2020 [[paper]](https://arxiv.org/abs/2001.04982)

### Unsupervised Intra-Domain Adaptation for Semantic Segmentation Through Self-Supervision CVPR 2020 [[paper]](https://openaccess.thecvf.com/content_CVPR_2020/html/Pan_Unsupervised_Intra-Domain_Adaptation_for_Semantic_Segmentation_Through_Self-Supervision_CVPR_2020_paper.html) [[PyTorch code]](https://github.com/feipan664/IntraDA)

### Weakly-supervised Cross-domain Adaptation for Endoscopic Lesions Segmentation IEEE TCSVT 2020 [[paper]]()

## 2019

### Adaptive Pyramid Context Network for Semantic Segmentation CVPR 2019 [[paper]](https://openaccess.thecvf.com/content_CVPR_2019/html/He_Adaptive_Pyramid_Context_Network_for_Semantic_Segmentation_CVPR_2019_paper.html)

### Asymmetric Non-Local Neural Networks for Semantic Segmentation ICCV 2019 [[paper]](http://openaccess.thecvf.com/content_ICCV_2019/html/Zhu_Asymmetric_Non-Local_Neural_Networks_for_Semantic_Segmentation_ICCV_2019_paper.html) [[code]](https://github.com/MendelXu/ANN)

### CCNet - Criss-Cross Attention for Semantic Segmentation ICCV 2019 [[paper]](http://openaccess.thecvf.com/content_ICCV_2019/html/Huang_CCNet_Criss-Cross_Attention_for_Semantic_Segmentation_ICCV_2019_paper.html)

### Dual Attention Network for Scene Segmentation CVPR 2019 [[CVPR paper]](http://openaccess.thecvf.com/content_CVPR_2019/html/Fu_Dual_Attention_Network_for_Scene_Segmentation_CVPR_2019_paper.html) [[arXiv paper]](https://arxiv.org/abs/1809.02983)

### Dynamic Multi-Scale Filters for Semantic Segmentation ICCV 2019 [[paper]](https://openaccess.thecvf.com/content_ICCV_2019/html/He_Dynamic_Multi-Scale_Filters_for_Semantic_Segmentation_ICCV_2019_paper.html)

### Stacked Deconvolutional Network for Semantic Segmentation IEEE TIP 2019 [[paper]](https://ieeexplore.ieee.org/document/8626494)

### Auto-DeepLab: Hierarchical Neural Architecture Search for Semantic Image Segmentation CVPR 2019 [[paper]](http://openaccess.thecvf.com/content_CVPR_2019/html/Liu_Auto-DeepLab_Hierarchical_Neural_Architecture_Search_for_Semantic_Image_Segmentation_CVPR_2019_paper.html)

### MHP-VOS: Multiple Hypotheses Propagation for Video Object Segmentation CVPR 2019 [[paper]](http://openaccess.thecvf.com/content_CVPR_2019/html/Xu_MHP-VOS_Multiple_Hypotheses_Propagation_for_Video_Object_Segmentation_CVPR_2019_paper.html)

### Co-Occurrent Features in Semantic Segmentation CVPR 2019 [[paper]](http://openaccess.thecvf.com/content_CVPR_2019/html/Zhang_Co-Occurrent_Features_in_Semantic_Segmentation_CVPR_2019_paper.html)

### Knowledge Adaptation for Efficient Semantic Segmentation CVPR 2019 [[paper]](http://openaccess.thecvf.com/content_CVPR_2019/html/He_Knowledge_Adaptation_for_Efficient_Semantic_Segmentation_CVPR_2019_paper.html)

### Learning Semantic Segmentation From Synthetic Data: A Geometrically Guided Input-Output Adaptation Approach CVPR 2019 [[paper]](http://openaccess.thecvf.com/content_CVPR_2019/html/Chen_Learning_Semantic_Segmentation_From_Synthetic_Data_A_Geometrically_Guided_Input-Output_CVPR_2019_paper.html)

### All About Structure: Adapting Structural Information Across Domains for Boosting Semantic Segmentation CVPR 2019 [[paper]](http://openaccess.thecvf.com/content_CVPR_2019/html/Chang_All_About_Structure_Adapting_Structural_Information_Across_Domains_for_Boosting_CVPR_2019_paper.html)

### Elastic Boundary Projection for 3D Medical Image Segmentation CVPR 2019 [[paper]](http://openaccess.thecvf.com/content_CVPR_2019/html/Ni_Elastic_Boundary_Projection_for_3D_Medical_Image_Segmentation_CVPR_2019_paper.html)

### ADVENT: Adversarial Entropy Minimization for Domain Adaptation in Semantic Segmentation CVPR 2019 [[paper]](http://openaccess.thecvf.com/content_CVPR_2019/html/Vu_ADVENT_Adversarial_Entropy_Minimization_for_Domain_Adaptation_in_Semantic_Segmentation_CVPR_2019_paper.html)

### Structured Knowledge Distillation for Semantic Segmentation CVPR 2019 [[paper]](http://openaccess.thecvf.com/content_CVPR_2019/html/Liu_Structured_Knowledge_Distillation_for_Semantic_Segmentation_CVPR_2019_paper.html)

### Decoders Matter for Semantic Segmentation: Data-Dependent Decoding Enables Flexible Feature Aggregation CVPR 2019 [[paper]](http://openaccess.thecvf.com/content_CVPR_2019/html/Tian_Decoders_Matter_for_Semantic_Segmentation_Data-Dependent_Decoding_Enables_Flexible_Feature_CVPR_2019_paper.html)

### Context-Reinforced Semantic Segmentation CVPR 2019 [[paper]](http://openaccess.thecvf.com/content_CVPR_2019/html/Zhou_Context-Reinforced_Semantic_Segmentation_CVPR_2019_paper.html)

### Pattern-Affinitive Propagation Across Depth, Surface Normal and Semantic Segmentation CVPR 2019 [[paper]](http://openaccess.thecvf.com/content_CVPR_2019/html/Zhang_Pattern-Affinitive_Propagation_Across_Depth_Surface_Normal_and_Semantic_Segmentation_CVPR_2019_paper.html)

### Not All Areas Are Equal: Transfer Learning for Semantic Segmentation via Hierarchical Region Selection CVPR 2019 [[paper]](http://openaccess.thecvf.com/content_CVPR_2019/html/Sun_Not_All_Areas_Are_Equal_Transfer_Learning_for_Semantic_Segmentation_CVPR_2019_paper.html)

### Hybrid Task Cascade for Instance Segmentation CVPR 2019 [[paper]](http://openaccess.thecvf.com/content_CVPR_2019/html/Chen_Hybrid_Task_Cascade_for_Instance_Segmentation_CVPR_2019_paper.html)

### An End-To-End Network for Panoptic Segmentation CVPR 2019 [[paper]](http://openaccess.thecvf.com/content_CVPR_2019/html/Liu_An_End-To-End_Network_for_Panoptic_Segmentation_CVPR_2019_paper.html)

### Bidirectional Learning for Domain Adaptation of Semantic Segmentation CVPR 2019 [[paper]](http://openaccess.thecvf.com/content_CVPR_2019/html/Li_Bidirectional_Learning_for_Domain_Adaptation_of_Semantic_Segmentation_CVPR_2019_paper.html)

### Attention-Guided Unified Network for Panoptic Segmentation CVPR 2019 [[paper]](http://openaccess.thecvf.com/content_CVPR_2019/html/Li_Attention-Guided_Unified_Network_for_Panoptic_Segmentation_CVPR_2019_paper.html)

### Triply Supervised Decoder Networks for Joint Detection and Segmentation CVPR 2019 [[paper]](http://openaccess.thecvf.com/content_CVPR_2019/html/Cao_Triply_Supervised_Decoder_Networks_for_Joint_Detection_and_Segmentation_CVPR_2019_paper.html)

### ZigZagNet: Fusing Top-Down and Bottom-Up Context for Object Segmentation CVPR 2019 [[paper]](http://openaccess.thecvf.com/content_CVPR_2019/html/Lin_ZigZagNet_Fusing_Top-Down_and_Bottom-Up_Context_for_Object_Segmentation_CVPR_2019_paper.html)

### Adaptive Pyramid Context Network for Semantic Segmentation CVPR 2019 [[paper]](http://openaccess.thecvf.com/content_CVPR_2019/html/He_Adaptive_Pyramid_Context_Network_for_Semantic_Segmentation_CVPR_2019_paper.html)

### UPSNet: A Unified Panoptic Segmentation Network CVPR 2019 [[paper]](http://openaccess.thecvf.com/content_CVPR_2019/html/Xiong_UPSNet_A_Unified_Panoptic_Segmentation_Network_CVPR_2019_paper.html)

### Improving Semantic Segmentation via Video Propagation and Label Relaxation CVPR 2019 [[CVPR paper]](http://openaccess.thecvf.com/content_CVPR_2019/html/Zhu_Improving_Semantic_Segmentation_via_Video_Propagation_and_Label_Relaxation_CVPR_2019_paper.html) [[arXiv paper]](https://arxiv.org/abs/1812.01593)

### Panoptic Segmentation CVPR 2019 [[paper]](http://openaccess.thecvf.com/content_CVPR_2019/html/Kirillov_Panoptic_Segmentation_CVPR_2019_paper.html)

### DFANet: Deep Feature Aggregation for Real-Time Semantic Segmentation CVPR 2019 [[paper]](http://openaccess.thecvf.com/content_CVPR_2019/html/Li_DFANet_Deep_Feature_Aggregation_for_Real-Time_Semantic_Segmentation_CVPR_2019_paper.html)

### Customizable Architecture Search for Semantic Segmentation CVPR 2019 [[paper]](http://openaccess.thecvf.com/content_CVPR_2019/html/Zhang_Customizable_Architecture_Search_for_Semantic_Segmentation_CVPR_2019_paper.html)

### SSAP: Single-Shot Instance Segmentation With Affinity Pyramid ICCV 2019 [[paper]](http://openaccess.thecvf.com/content_ICCV_2019/html/Gao_SSAP_Single-Shot_Instance_Segmentation_With_Affinity_Pyramid_ICCV_2019_paper.html)

### InstaBoost: Boosting Instance Segmentation via Probability Map Guided Copy-Pasting ICCV 2019 [[paper]](http://openaccess.thecvf.com/content_ICCV_2019/html/Fang_InstaBoost_Boosting_Instance_Segmentation_via_Probability_Map_Guided_Copy-Pasting_ICCV_2019_paper.html)

### SSF-DAN: Separated Semantic Feature Based Domain Adaptation Network for Semantic Segmentation ICCV 2019 [[paper]](http://openaccess.thecvf.com/content_ICCV_2019/html/Du_SSF-DAN_Separated_Semantic_Feature_Based_Domain_Adaptation_Network_for_Semantic_ICCV_2019_paper.html)

### TensorMask: A Foundation for Dense Object Segmentation ICCV 2019 [[paper]](http://openaccess.thecvf.com/content_ICCV_2019/html/Chen_TensorMask_A_Foundation_for_Dense_Object_Segmentation_ICCV_2019_paper.html)

### Domain Adaptation for Semantic Segmentation With Maximum Squares Loss ICCV 2019 [[paper]](http://openaccess.thecvf.com/content_ICCV_2019/html/Chen_Domain_Adaptation_for_Semantic_Segmentation_With_Maximum_Squares_Loss_ICCV_2019_paper.html)

### Efficient Segmentation: Learning Downsampling Near Semantic Boundaries ICCV 2019 [[paper]](http://openaccess.thecvf.com/content_ICCV_2019/html/Marin_Efficient_Segmentation_Learning_Downsampling_Near_Semantic_Boundaries_ICCV_2019_paper.html)

### Recurrent U-Net for Resource-Constrained Segmentation ICCV 2019 [[paper]](http://openaccess.thecvf.com/content_ICCV_2019/html/Wang_Recurrent_U-Net_for_Resource-Constrained_Segmentation_ICCV_2019_paper.html)

### Dynamic Multi-Scale Filters for Semantic Segmentation ICCV 2019 [[paper]](http://openaccess.thecvf.com/content_ICCV_2019/html/He_Dynamic_Multi-Scale_Filters_for_Semantic_Segmentation_ICCV_2019_paper.html)

### Towards Bridging Semantic Gap to Improve Semantic Segmentation ICCV 2019 [[paper]](http://openaccess.thecvf.com/content_ICCV_2019/html/Pang_Towards_Bridging_Semantic_Gap_to_Improve_Semantic_Segmentation_ICCV_2019_paper.html)

### Explicit Shape Encoding for Real-Time Instance Segmentation ICCV 2019 [[paper]](http://openaccess.thecvf.com/content_ICCV_2019/html/Xu_Explicit_Shape_Encoding_for_Real-Time_Instance_Segmentation_ICCV_2019_paper.html)

### Gated-SCNN: Gated Shape CNNs for Semantic Segmentation ICCV 2019 [[paper]](http://openaccess.thecvf.com/content_ICCV_2019/html/Takikawa_Gated-SCNN_Gated_Shape_CNNs_for_Semantic_Segmentation_ICCV_2019_paper.html)

### Significance-Aware Information Bottleneck for Domain Adaptive Semantic Segmentation ICCV 2019 [[paper]](http://openaccess.thecvf.com/content_ICCV_2019/html/Luo_Significance-Aware_Information_Bottleneck_for_Domain_Adaptive_Semantic_Segmentation_ICCV_2019_paper.html)

### (ACFNet) ACFNet Attentional Class Feature Network for Semantic Segmentation ICCV 2019 [[paper]](https://arxiv.org/abs/1909.09408)

### Boundary-Aware Feature Propagation for Scene Segmentation ICCV 2019 [[paper]](http://openaccess.thecvf.com/content_ICCV_2019/html/Ding_Boundary-Aware_Feature_Propagation_for_Scene_Segmentation_ICCV_2019_paper.html)

### Prior-Aware Neural Network for Partially-Supervised Multi-Organ Segmentation ICCV 2019 [[paper]](http://openaccess.thecvf.com/content_ICCV_2019/html/Zhou_Prior-Aware_Neural_Network_for_Partially-Supervised_Multi-Organ_Segmentation_ICCV_2019_paper.html)

### Expectation-Maximization Attention Networks for Semantic Segmentation ICCV 2019 (Oral) [[paper]](https://arxiv.org/abs/1907.13426) [[code]](https://github.com/XiaLiPKU/EMANet)

### SPGNet: Semantic Prediction Guidance for Scene Parsing [[paper]](http://openaccess.thecvf.com/content_ICCV_2019/html/Cheng_SPGNet_Semantic_Prediction_Guidance_for_Scene_Parsing_ICCV_2019_paper.html)

### Adaptive Context Network for Scene Parsing [[paper]](http://openaccess.thecvf.com/content_ICCV_2019/html/Fu_Adaptive_Context_Network_for_Scene_Parsing_ICCV_2019_paper.html)

### Category Anchor-Guided Unsupervised Domain Adaptation for Semantic Segmentation NIPS 2019 [[paper]](https://papers.nips.cc/paper/8335-category-anchor-guided-unsupervised-domain-adaptation-for-semantic-segmentation)

### Neural Diffusion Distance for Image Segmentation NIPS 2019 [[paper]](https://papers.nips.cc/paper/8424-neural-diffusion-distance-for-image-segmentation)

### Exploiting Local and Global Structure for Point Cloud Semantic Segmentation with Contextual Point Representations NIPS 2019 [[paper]](https://papers.nips.cc/paper/8706-exploiting-local-and-global-structure-for-point-cloud-semantic-segmentation-with-contextual-point-representations)

### Topology-Preserving Deep Image Segmentation NIPS 2019 [[paper]](https://papers.nips.cc/paper/8803-topology-preserving-deep-image-segmentation)

### Region Mutual Information Loss for Semantic Segmentation NIPS 2019 [[paper]](https://papers.nips.cc/paper/9291-region-mutual-information-loss-for-semantic-segmentation)

### Grid Saliency for Context Explanations of Semantic Segmentation NIPS 2019 [[paper]](https://papers.nips.cc/paper/8874-grid-saliency-for-context-explanations-of-semantic-segmentation)

### Multi-source Domain Adaptation for Semantic Segmentation NIPS 2019 [[paper]](https://papers.nips.cc/paper/8949-multi-source-domain-adaptation-for-semantic-segmentation)

### Stacked U-Nets: A No-Frills Approach to Natural Image Segmentation [[paper]](https://openreview.net/forum?id=BJgFcj0qKX)

### Seamless Scene Segmentation CVPR 2019 [[paper]](http://openaccess.thecvf.com/content_CVPR_2019/html/Porzi_Seamless_Scene_Segmentation_CVPR_2019_paper.html)

### Panoptic-DeepLab ICCVW 2019 [[paper]](https://arxiv.org/abs/1910.04751)

### PolyTransform: Deep Polygon Transformer for Instance Segmentation arXiv 2019 [[paper]](https://arxiv.org/abs/1912.02801)

### Object Instance Annotation With Deep Extreme Level Set Evolution CVPR 2019 [[paper]](https://openaccess.thecvf.com/content_CVPR_2019/html/Wang_Object_Instance_Annotation_With_Deep_Extreme_Level_Set_Evolution_CVPR_2019_paper.html)

### Object-Contextual Representations for Semantic Segmentation arXiv 2019 [[paper]](https://arxiv.org/abs/1909.11065)

## 2018

### A Fully Convolutional Two-Stream Fusion Network for Interactive Image Segmentation Neural Networks 2019 [[paper]](https://arxiv.org/abs/1807.02480) [[NN paper]](https://www.sciencedirect.com/science/article/pii/S0893608018302946)

### Adaptive Affinity Fields for Semantic Segmentation ECCV 2018 [[paper]](http://openaccess.thecvf.com/content_ECCV_2018/html/Jyh-Jing_Hwang_Adaptive_Affinity_Field_ECCV_2018_paper.html)

### Adversarial Structure Matching Loss for Image Segmentation 2018 [[paper]](https://arxiv.org/abs/1805.07457)

### Affinity Derivation and Graph Merge for Instance Segmentation ECCV 2018 [[paper]](http://openaccess.thecvf.com/content_ECCV_2018/html/Yiding_Liu_Affinity_Derivation_and_ECCV_2018_paper.html)

### Associating Inter-Image Salient Instances for Weakly Supervised Semantic Segmentation ECCV 2018 [[paper]](http://openaccess.thecvf.c## 2015

### Bayesian SegNet Model Uncertainty in Deep Convolutional Encoder-Decoder Architectures for Scene Understanding [[paper]](https://arxiv.org/abs/1511.02680)

### BoxSup Exploiting Bounding Boxes to Supervise Convolutional Networks for Semantic Segmentation ICCV 2015 [[paper]](https://www.cv-foundation.org/openaccess/content_iccv_2015/papers/Dai_BoxSup_Exploiting_Bounding_ICCV_2015_paper.pdf)

### (CRFasRNN) Conditional Random Fields as Recurrent Neural Networks [[paper]](http://www.robots.ox.ac.uk/~szheng/papers/CRFasRNN.pdf)

### Feedforward Semantic Segmentation with Zoom-out Features CVPR 2015 [[paper]](https://arxiv.org/abs/1412.0774)

### Fully Connected Deep Structured Networks [[paper]](https://arxiv.org/abs/1503.02351)

### (FCN) Fully Convolutional Networks for Semantic Segmentation CVPR [[paper]](http://www.cv-foundation.org/openaccess/content_cvpr_2015/papers/Long_Fully_Convolutional_Networks_2015_CVPR_paper.pdf)

"the first work on FCN for semantic segmentation", "VOC 2012: 62.2 mAP"

### Hypercolumns for Object Segmentation and Fine-grained Localization [[paper]](https://www.cv-foundation.org/openaccess/content_cvpr_2015/papers/Hariharan_Hypercolumns_for_Object_2015_CVPR_paper.pdf)

### Monocular Object Instance Segmentation and Depth Ordering with CNNs ICCV 2015 [[paper]](https://ieeexplore.ieee.org/document/7410657/)

### Multi-scale Context Aggregation by Dilated Convolutions [[paper]](http://arxiv.org/abs/1511.07122)

"VOC 2012: 75.3 mAP"

### SegNet A Deep Convolutional Encoder-Decoder Architecture for Image Segmentation [[paper]](https://arxiv.org/abs/1511.00561) [[TPAMI version]](http://ieeexplore.ieee.org/document/7803544/)

"VOC 2012: 59.9 mAP"

### SegNet A Deep Convolutional Encoder-Decoder Architecture for Robust Semantic Pixel-wise Labelling [[paper]](https://arxiv.org/abs/1505.07293)

### Semantic Image Segmentation via Deep Parsing Network ICCV 2015 [[paper]](http://www.cv-foundation.org/openaccess/content_iccv_2015/html/Liu_Semantic_Image_Segmentation_ICCV_2015_paper.html)

### U-Net Convolutional Networks for Biomedical Image Segmentation MICCAI 2015 [[paper]](https://link.springer.com/chapter/10.1007/978-3-319-24574-4_28)

### Weakly and Semi-supervised Learning of a DCNN for Semantic Image Segmentation [[paper]](http://openaccess.thecvf.com/content_iccv_2015/papers/Papandreou_Weakly-_and_Semi-Supervised_ICCV_2015_paper.pdf)

om/content_ECCV_2018/html/Ruochen_Fan_Associating_Inter-Image_Salient_ECCV_2018_paper.html)

### Attention-guided Unified Network for Panoptic Segmentation 2018 [[paper]](https://arxiv.org/abs/1812.03904)

### Bayesian Semantic Instance Segmentation in Open Set World ECCV 2018 [[paper]](http://openaccess.thecvf.com/content_ECCV_2018/html/Trung_Pham_Bayesian_Instance_Segmentation_ECCV_2018_paper.html)

### (BiSeNet) BiSeNet Bilateral Segmentation Network for Real-time Semantic Segmentation ECCV 2018 [[paper]](http://openaccess.thecvf.com/content_ECCV_2018/html/Changqian_Yu_BiSeNet_Bilateral_Segmentation_ECCV_2018_paper.html)

""

### CIAN - Cross-Image Affinity Net for Weakly Supervised Semantic Segmentation arXiv 2018 [[paper]](https://arxiv.org/abs/1811.10842)

### Concentrated-Comprehensive Convolutions for Lightweight Semantic Segmentation arXiv 2018 [[paper]](https://arxiv.org/abs/1812.04920)

### Context Contrasted Feature and Gated Multi-Scale Aggregation for Scene Segmentation CVPR 2018 [[paper]](http://openaccess.thecvf.com/content_cvpr_2018/html/Ding_Context_Contrasted_Feature_CVPR_2018_paper.html)

### Context Encoding for Semantic Segmentation CVPR 2018  [[cvpr paper]](https://openaccess.thecvf.com/content_cvpr_2018/html/Zhang_Context_Encoding_for_CVPR_2018_paper.html) [[arXiv paper]](https://arxiv.org/abs/1803.08904) [[Pytorch code]](https://hangzhang.org/PyTorch-Encoding/experiments/segmentation.html)

""

### ContextNet Exploring Context and Detail for Semantic Segmentation in Real-time 2018 [[paper]](https://arxiv.org/abs/1805.04554)

### Convolutional CRFs for Semantic Segmentation 2018 [[paper]](https://arxiv.org/abs/1805.04777) [[code]](https://github.com/MarvinTeichmann/ConvCRF)

### Deep Extreme Cut From Extreme Points to Object Segmentation CVPR 2018 [[paper]](http://openaccess.thecvf.com/content_cvpr_2018/papers/Maninis_Deep_Extreme_Cut_CVPR_2018_paper.pdf)

### Deep Learning Markov Random Field for Semantic Segmentation IEEE TPAMI 2018[[paper]](https://ieeexplore.ieee.org/document/8006236)

### Deep Object Co-Segmentation 2018 [[paper]](https://arxiv.org/abs/1804.06423)

### (DeepLab V2) DeepLab - Semantic Image Segmentation with Deep Convolutional Nets - Atrous Convolution - and Fully Connected CRFs IEEE TPAMI 2018 [[arXiv paper]](http://arxiv.org/abs/1606.00915) [[PAMI paper]](https://ieeexplore.ieee.org/document/7913730)

"PASCAL VOC 2012: 79.7 mIoU"

### DenseASPP for Semantic Segmentation in Street Scenes CVPR 2018 [[paper]](https://openaccess.thecvf.com/content_cvpr_2018/html/Yang_DenseASPP_for_Semantic_CVPR_2018_paper.html)

### Depth-aware CNN for RGB-D Segmentation ECCV 2018 [[paper]](http://openaccess.thecvf.com/content_ECCV_2018/html/Weiyue_Wang_Depth-aware_CNN_for_ECCV_2018_paper.html)

### Diagnostics in Semantic Segmentation 2018 [[paper]](https://arxiv.org/abs/1809.10328)

### DSNet for Real-Time Driving Scene Semantic Segmentation 2018 [[paper]](https://arxiv.org/abs/1812.07049)

### Dynamic Video Segmentation Network CVPR 2018 [[paper]](http://openaccess.thecvf.com/content_cvpr_2018/papers/Xu_Dynamic_Video_Segmentation_CVPR_2018_paper.pdf)

### Efficient Dense Modules of Asymmetric Convolution for Real-Time Semantic Segmentation 2018 [[paper]](https://arxiv.org/abs/1809.06323)

### Efficient Uncertainty Estimation for Semantic Segmentation in Videos ECCV 2018 [[paper]](http://openaccess.thecvf.com/content_ECCV_2018/html/Po-Yu_Huang_Efficient_Uncertainty_Estimation_ECCV_2018_paper.html)

### (DeepLab V3+) Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentation ECCV 2018 [[arXiv paper]](https://arxiv.org/abs/1802.02611)

### End-to-End Joint Semantic Segmentation of Actors and Actions in Video ECCV 2018 [[paper]](http://openaccess.thecvf.com/content_ECCV_2018/html/Jingwei_Ji_End-to-End_Joint_Semantic_ECCV_2018_paper.html)

### ESPNet Efficient Spatial Pyramid of Dilated Convolutions for Semantic Segmentation ECCV 2018 [[paper]](http://openaccess.thecvf.com/content_ECCV_2018/html/Sachin_Mehta_ESPNet_Efficient_Spatial_ECCV_2018_paper.html)

### ESPNetv2 A Light-weight Power Efficient and General Purpose Convolutional Neural Network ArXiv 2018 [[paper]](https://arxiv.org/abs/1811.11431) [[code]](https://github.com/sacmehta/ESPNetv2)

### ExFuse - Enhancing Feature Fusion for Semantic Segmentation ECCV 2018 [[paper]](https://arxiv.org/abs/1804.03821)

### Exploring Context with Deep Structured models for Semantic Segmentation IEEE TPAMI 2018 [[paper]](http://ieeexplore.ieee.org/document/7934393/)

### Exploring New Backbone and Attention Module for Semantic Segmentation in Street Scenes IEEE Access 2018 [[paper]](https://ieeexplore.ieee.org/document/8531594)

### Fast Neural Architecture Search of Compact Semantic Segmentation Models via Auxiliary Cells ArXiv 2018 [[paper]](https://arxiv.org/abs/1810.10804)

### Faster Training of Mask R-CNN by Focusing on Instance Boundaries 2018 [[paper]](https://arxiv.org/abs/1809.07069)

### Geometric Constrained Joint Lane Segmentation and Lane Boundary Detection ECCV 2018 [[paper]](http://openaccess.thecvf.com/content_ECCV_2018/html/Jie_Zhang_Geometric_Constrained_Joint_ECCV_2018_paper.html)

### Guide Me Interacting with Deep Networks CVPR 2018 [[paper]](http://openaccess.thecvf.com/content_cvpr_2018/papers/Rupprecht_Guide_Me_Interacting_CVPR_2018_paper.pdf)

### ICNet for Real-Time Semantic Segmentation on High-Resolution Images ECCV 2018 [[paper]](http://openaccess.thecvf.com/content_ECCV_2018/html/Hengshuang_Zhao_ICNet_for_Real-Time_ECCV_2018_paper.html)

### Interactive Full Image Segmentation 2018 [[paper]](https://arxiv.org/abs/1812.01888)

### Interactive Image Segmentation with Latent Diversity CVPR 2018 [[paper]](http://openaccess.thecvf.com/content_cvpr_2018/papers/Li_Interactive_Image_Segmentation_CVPR_2018_paper.pdf)

### Iteratively Trained Interactive Segmentation 2018 [[paper]](https://arxiv.org/abs/1805.04398)

### (DFN) Learning a Discriminative Feature Network for Semantic Segmentation CVPR 2018 [[paper]](https://arxiv.org/abs/1804.09337)

"Smooth Network for intra-class inconsistency using global pooling layer at the end of encoder, and Border Network for inter-class indistinction using focal loss as boundary loss", "deep supervision in both Smooth and Border Networks", "similarly in stacked hourglass networks, skip connection with tranformation including (Refinement Residual Block, proposed in RefineNet) RRB and (Channel Attention Block, proposed in SENet) CAB is used in this paper", "this paper combines many known tricks"

### Learning Discriminators as Energy Networks in Adversarial Learning 2018 [[paper]](https://arxiv.org/abs/1810.01152)

### Learning to Segment via Cut-and-Paste ECCV 2018 [[paper]](http://openaccess.thecvf.com/content_ECCV_2018/html/Tal_Remez_Learning_to_Segment_ECCV_2018_paper.html)

### Leveraging Motion Priors in Videos for Improving Human Segmentation ECCV 2018 [[paper]](http://openaccess.thecvf.com/content_ECCV_2018/html/Yu-Ting_Chen_Leveraging_Motion_Priors_ECCV_2018_paper.html)

### Light-Weight RefineNet for Real-Time Semantic Segmentation BMVC 2018 [[paper]](https://arxiv.org/abs/1810.03272)

### MobileNetV2 Inverted Residuals and Linear Bottlenecks CVPR 2018 [[paper]](https://arxiv.org/abs/1801.04381) [[CVPR version]](http://openaccess.thecvf.com/content_cvpr_2018/papers/Sandler_MobileNetV2_Inverted_Residuals_CVPR_2018_paper.pdf)

### Multi-Scale Context Intertwining for Semantic Segmentation ECCV 2018 [[paper]](http://openaccess.thecvf.com/content_ECCV_2018/html/Di_Lin_Multi-Scale_Context_Intertwining_ECCV_2018_paper.html)

### OCNet Object Context Network for Scene Parsing ArXiv [[paper]](https://arxiv.org/abs/1809.00916)

### Panoptic Segmentation 2018 [[paper]](https://arxiv.org/abs/1801.00868)

"introduction of panoptic segmentation"

### Panoptic Segmentation with a Joint Semantic and Instance Segmentation Network 2018 [[paper]](https://arxiv.org/abs/1809.02110)

"JSIS-Net"

### (PAN/PANet) Path Aggregation Network for Instance Segmentation CVPR 2018 [[paper]](https://arxiv.org/abs/1803.01534)

### Penalizing Top Performers: Conservative Loss for Semantic Segmentation Adaptation ECCV 2018 [[paper]](http://openaccess.thecvf.com/content_ECCV_2018/html/Xinge_Zhu_Penalizing_Top_Performers_ECCV_2018_paper.html)

### (PersonLab) PersonLab Person Pose Estimation and Instance Segmentation with a Bottom-Up, Part-Based, Geometric Embedding Model ECCV 2018 [[paper]](http://openaccess.thecvf.com/content_ECCV_2018/html/George_Papandreou_PersonLab_Person_Pose_ECCV_2018_paper.html)

### Progressive Refinement a Method of Coarse-to-fine Image Parsing Using Stacked Network 2018 [[paper]](https://arxiv.org/abs/1804.08256)

### (PSANet) PSANet - Point-wise Spatial Attention Network for Scene Parsing ECCV 2018 [[paper]](https://openaccess.thecvf.com/content_ECCV_2018/html/Hengshuang_Zhao_PSANet_Point-wise_Spatial_ECCV_2018_paper.html)

### Pyramid Attention Network for Semantic Segmentation ArXiv 2018 [[paper]](https://arxiv.org/abs/1805.10180)

### Revisiting Dilated Convolution A Simple Approach for Weakly- and Semi- Supervised Semantic Segmentation 2018 [[paepr]](https://arxiv.org/abs/1805.04574)

### Searching for Efficient Multi-Scale Architectures for Dense Image Prediction NIPS 2018 [[paper]](https://arxiv.org/abs/1809.04184)

"Liang-Chieh Chen's new work on NAS and Dense Image Prediction, including scene parsing, person-part segmentation and semantic image segmentation"

### SeedNet Automatic Seed Generation with Deep Reinforcement Learning for Robust Interactive Segmentation CVPR 2018 [[paper]](http://openaccess.thecvf.com/content_cvpr_2018/papers/Song_SeedNet_Automatic_Seed_CVPR_2018_paper.pdf)

### Semantic Aware Attention Based Deep Object Co-segmentation 2018 [[paper]](https://arxiv.org/abs/1810.06859)

### Semantic Segmentation With Global Encoding and Dilated Decoder in Street Scenes IEEE Access 2018 [[paper]](https://ieeexplore.ieee.org/document/8454723)

### Semantic Soft Segmentation ACM TOG 2018 [[paper]](http://people.inf.ethz.ch/aksoyy/papers/TOG18-sss.pdf) [[project]](http://people.inf.ethz.ch/aksoyy/sss/)

### Semi-convolutional Operators for Instance Segmentation ECCV 2018 [[paper]](http://openaccess.thecvf.com/content_ECCV_2018/html/Samuel_Albanie_Semi-convolutional_Operators_for_ECCV_2018_paper.html)

### ShelfNet for Real-time Semantic Segmentation 2018 [[paper]](https://arxiv.org/abs/1811.11254)

### SwipeCut Interactive Segmentation with Diversified Seed Proposals 2018 [[paper]](https://arxiv.org/abs/1812.07260)

### TernausNet U-Net with VGG11 Encoder Pre-Trained on ImageNet for Image Segmentation [[paper]](https://arxiv.org/abs/1801.05746)

### The Lovász-Softmax Loss A Tractable Surrogate for the Optimization of the Intersection-over-union Measure in Neural Networks CVPR 2018 [[code]](https://github.com/bermanmaxim/jaccardSegment)

### Tree-structured Kronecker Convolutional Network for Semantic Segmentation ArXiv 2018 [[paper]](https://arxiv.org/abs/1812.04945) [[Pytorch code]](https://github.com/wutianyiRosun/TKCN)

### Triply Supervised Decoder Networks for Joint Detection and Segmentation ArXiv 2018 [[paper]](https://arxiv.org/abs/1809.09299)

### Understanding Convolution for Semantic Segmentation IEEE WACV 2018 [[arXiv paper]](https://arxiv.org/abs/1702.08502)

"Figure 5. Effectiveness of HDC (Hybrid Dilated Convolution) in eliminating the gridding effect."

### Unified Perceptual Parsing for Scene Understanding ECCV 2018 [[paper]](https://openaccess.thecvf.com/content_ECCV_2018/html/Tete_Xiao_Unified_Perceptual_Parsing_ECCV_2018_paper.html)

### Unsupervised Domain Adaptation for Semantic Segmentation via Class-Balanced Self-Training ECCV 2018 [[paper]](http://openaccess.thecvf.com/content_ECCV_2018/html/Yang_Zou_Unsupervised_Domain_Adaptation_ECCV_2018_paper.html)

### Unsupervised Video Object Segmentation Using Motion Saliency-Guided Spatio-Temporal Propagation ECCV 2018 [[paper]](http://openaccess.thecvf.com/content_ECCV_2018/html/Yuan-Ting_Hu_Unsupervised_Video_Object_ECCV_2018_paper.html)

### Unsupervised Video Object Segmentation with Motion-based Bilateral Networks ECCV 2018 [[paper]](http://openaccess.thecvf.com/content_ECCV_2018/html/Siyang_Li_Unsupervised_Video_Object_ECCV_2018_paper.html)

### Video Object Segmentation by Learning Location-Sensitive Embeddings ECCV 2018 [[paper]](http://openaccess.thecvf.com/content_ECCV_2018/html/Hai_Ci_Video_Object_Segmentation_ECCV_2018_paper.html)

### Video Object Segmentation with Joint Re-identification and Attention-Aware Mask Propagation ECCV 2018 [[paper]](http://openaccess.thecvf.com/content_ECCV_2018/html/Xiaoxiao_Li_Video_Object_Segmentation_ECCV_2018_paper.html)

### Weakly Supervised Instance Segmentation Using Class Peak Response CVPR 2018 [[paper]](https://arxiv.org/abs/1804.00880)

### Weakly- and Semi-Supervised Panoptic Segmentation ECCV 2018 [[paper]](http://openaccess.thecvf.com/content_ECCV_2018/html/Anurag_Arnab_Weakly-_and_Semi-Supervised_ECCV_2018_paper.html)

### YouTube-VOS Sequence-to-Sequence Video Object Segmentation ECCV 2018 [[paper]](http://openaccess.thecvf.com/content_ECCV_2018/html/Ning_Xu_YouTube-VOS_Sequence-to-Sequence_Video_ECCV_2018_paper.html)

## 2017

### BlitzNet A Real-Time Deep Network for Scene Understanding ICCV 2017 [[paper]](http://openaccess.thecvf.com/content_iccv_2017/html/Dvornik_BlitzNet_A_Real-Time_ICCV_2017_paper.html)

### Boundary-Aware Instance Segmentation CVPR 2017 [[paper]](https://openaccess.thecvf.com/content_cvpr_2017/html/Hayder_Boundary-Aware_Instance_Segmentation_CVPR_2017_paper.html) [[arXiv]](https://arxiv.org/abs/1612.03129)

### Convolutional Random Walk Networks for Semantic Image Segmentation CVPR 2017 [[paper]](http://openaccess.thecvf.com/content_cvpr_2017/html/Bertasius_Convolutional_Random_Walk_CVPR_2017_paper.html)

### Deep Dual Learning for Semantic Image Segmentation ICCV 2017 [[paper]](http://openaccess.thecvf.com/content_iccv_2017/html/Luo_Deep_Dual_Learning_ICCV_2017_paper.html)

### Deep GrabCut for Object Selection BMVC 2017 [[paper]](https://arxiv.org/abs/1707.00243)

### Deep Watershed Transform for Instance Segmentation CVPR 2017 [[paper]](http://openaccess.thecvf.com/content_cvpr_2017/html/Bai_Deep_Watershed_Transform_CVPR_2017_paper.html)

"combination of watershed and neural networks"

### Densely Connected Deconvolutional Network for Semantic Segmentation IEEE TIP 2017[[paper]](https://ieeexplore.ieee.org/abstract/document/8296850/)

### Discovering Class-Specific Pixels for Weakly-Supervised Semantic Segmentation BMVC 2017 [[paper]](https://arxiv.org/abs/1707.05821)

### End-to-end Semantic Face Segmentation with Conditional Random Fields as Convolutional Recurrent and Adversarial Networks [[paper]](https://arxiv.org/abs/1703.03305)

### Exploiting Saliency for Object Segmentation From Image Level Labels CVPR 2017 [[paper]](http://openaccess.thecvf.com/content_cvpr_2017/html/Oh_Exploiting_Saliency_for_CVPR_2017_paper.html)

### Face Parsing via Recurrent Propagation arXiv 2017 [[paper]](https://arxiv.org/abs/1708.01936)

### Fully Convolutional Instance-aware Semantic Segmentation CVPR 2017 [[paper]](https://arxiv.org/abs/1611.07709)

### Gated Feedback Refinement Network for Dense Image Labeling CVPR 2017[[paper]](http://openaccess.thecvf.com/content_cvpr_2017/papers/Islam_Gated_Feedback_Refinement_CVPR_2017_paper.pdf) [[code]](https://github.com/mrochan/gfrnet)

### InstanceCut: from Edges to Instances with MultiCut CVPR 2017 [[paper]](https://arxiv.org/abs/1611.08272)

### Large Kernel Matters - Improve Semantic Segmentation by Global Convolutional Network CVPR 2017 [[paper]](https://arxiv.org/abs/1703.02719)

"VOC 2012: 82.2 mAP"

### Learning Affinity via Spatial Propagation Networks arXiv 2017 [[paper]](https://arxiv.org/abs/1710.01020)

### Learning to Segment Instances in Videos with Spatial Propagation Network arXiv 2017 [[paper]](https://arxiv.org/abs/1709.04609)

### Learning Multi-level Region Consistency with Dense Multi-label Networks for Semantic Segmentation IJCAI 2017 [[paper]](https://arxiv.org/abs/1701.07122)

### Learning Video Object Segmentation from Static Images CVPR 2017 [[paper]](http://openaccess.thecvf.com/content_cvpr_2017/papers/Perazzi_Learning_Video_Object_CVPR_2017_paper.pdf)

### LinkNet - Exploiting encoder representations for efficient semantic segmentation IEEE VCIP 2017 [[paper]](https://ieeexplore.ieee.org/document/8305148) [[arXiv paper]](https://arxiv.org/abs/1707.03718) [[Torch code]](https://github.com/e-lab/LinkNet)

### Mask R-CNN ICCV 2017 [[paper]](http://openaccess.thecvf.com/content_iccv_2017/html/He_Mask_R-CNN_ICCV_2017_paper.html)

### MaskLab Instance Segmentation by Refining Object Detection with Semantic and Direction Features arXiv 2017 [[paper]](https://arxiv.org/abs/1712.04837)

### Mix-and-Match Tuning for Self-Supervised Semantic Segmentation arXiv 2017[[paper]](https://arxiv.org/abs/1712.00661)

### Not All Pixels Are Equal Difficulty-aware Semantic Segmentation via Deep Layer Cascade CVPR 2017 [[arXiv paper]](https://arxiv.org/abs/1704.01344)

### Object Region Mining With Adversarial Erasing A Simple Classification to Semantic Segmentation Approach CVPR 2017 [[paper]](http://openaccess.thecvf.com/content_cvpr_2017/html/Wei_Object_Region_Mining_CVPR_2017_paper.html)

### Online Video Object Segmentation via Convolutional Trident Network CVPR 2017 [[paper]](http://openaccess.thecvf.com/content_cvpr_2017/papers/Jang_Online_Video_Object_CVPR_2017_paper.pdf)

### Pixel Deconvolutional Networks arXiv 2017 [[paper]](https://arxiv.org/abs/1705.06820)

### Pixelwise Instance Segmentation with a Dynamically Instantiated Network CVPR 2017 [[paper]](http://openaccess.thecvf.com/content_cvpr_2017/html/Arnab_Pixelwise_Instance_Segmentation_CVPR_2017_paper.html)

### (PSPNet) Pyramid Scene Parsing Network CVPR 2017 [[arXiv paper]](https://arxiv.org/abs/1612.01105) [[paper]](https://openaccess.thecvf.com/content_cvpr_2017/html/Zhao_Pyramid_Scene_Parsing_CVPR_2017_paper.html)

"PASCAL VOC 2012: 85.4 mAP"

### Real-time Semantic Image Segmentation via Spatial Sparsity 2017 [[paper]](https://arxiv.org/abs/1712.00213)

### RefineNet Multi-Path Refinement Networks for High-Resolution Semantic Segmentation CVPR 2017 [[paper]](https://arxiv.org/abs/1611.06612)

"PASCAL VOC 2012: 84.2 mAP"

### Regional Interactive Image Segmentation Networks ICCV 2017 [[paper]](http://openaccess.thecvf.com/content_iccv_2017/html/Liew_Regional_Interactive_Image_ICCV_2017_paper.html)

### Residual Conv-Deconv Grid Network for Semantic Segmentation [[paper]](https://arxiv.org/abs/1707.07958)

### (DeepLab V3) Rethinking Atrous Convolution for Semantic Image Segmentation [[arXiv paper]](https://arxiv.org/abs/1706.05587)

"PASCAL VOC 2012: 85.7 mIoU"

### Scene Parsing with Global Context Embedding ICCV 2017 [[paper]](https://openaccess.thecvf.com/content_iccv_2017/html/Hung_Scene_Parsing_With_ICCV_2017_paper.html)

"PASCAL-Context validation set: 46.52 mIoU", "ADE20K validation set: 38.37 mIoU"

### SegNet - A Deep Convolutional Encoder-Decoder Architecture for Image Segmentation IEEE TPAMI 2017 [[TPAMI paper]](http://ieeexplore.ieee.org/document/7803544/) [[arXiv paper]](https://arxiv.org/abs/1511.00561) 

"PASCAL VOC 2012: 59.9 mIoU"

### Semantic Instance Segmentation with a Discriminative Loss Function CVPRW 2017 [[arXiv paper]](https://arxiv.org/abs/1708.02551)

### Semantic Segmentation via Structured Patch Prediction, Context CRF and Guidance CRF CVPR 2017 [[papaer]](http://openaccess.thecvf.com/content_cvpr_2017/papers/Shen_Semantic_Segmentation_via_CVPR_2017_paper.pdf)

### SGN Sequential Grouping Networks for Instance Segmentation ICCV 2017 [[paper]](http://openaccess.thecvf.com/content_iccv_2017/html/Liu_SGN_Sequential_Grouping_ICCV_2017_paper.html)

### Simple Does It Weakly Supervised Instance and Semantic Segmentation CVPR 2017 [[paper]](http://openaccess.thecvf.com/content_cvpr_2017/papers/Khoreva_Simple_Does_It_CVPR_2017_paper.pdf)

### STC A Simple to Complex Framework for Weakly-Supervised Semantic Segmentation IEEE TPAMI 2017 [[paper]](https://ieeexplore.ieee.org/document/7775087/)

### Stacked Deconvolutional Network for Semantic Segmentation [[paper]](https://arxiv.org/abs/1708.04943)

### Superpixel-based Semantic Segmentation Trained by Statistical Process Control [[paper]](https://arxiv.org/abs/1706.10071)

### The Devil is in the Decoder arXiv 2017 [[paper]](https://arxiv.org/abs/1707.05847)

### Universal Adversarial Perturbations Against Semantic Image Segmentation arXiv 2017 [[paper]](https://arxiv.org/abs/1704.05712)

### Video Object Segmentation with Re-identification arXiv 2017[[paper]](https://arxiv.org/abs/1708.00197)

## 2016

### Attention to Scale Scale-aware Semantic Image Segmentation CVPR 2016 [[paper]](https://arxiv.org/abs/1511.03339)

### ScribbleSup Scribble-supervised Convolutional Networks for Semantic Segmentation CVPR 2016 [[paper]](http://arxiv.org/abs/1604.05144)

### Bottom-up Instance Segmentation Using Deep Higher-order CRFs BMVC 2016 [[paper]](http://arxiv.org/abs/1609.02583)

### Bridging Category-level and Instance-level Semantic Image Segmentation [[paper]](https://arxiv.org/abs/1605.06885)

### Deep Interactive Object Selection CVPR 2016 [[paper]](https://arxiv.org/abs/1603.04042)

### Efficient Piecewise Training of Deep Structured Models for Semantic Segmentation CVPR 2016 [[paper]](http://www.cv-foundation.org/openaccess/content_cvpr_2016/papers/Lin_Efficient_Piecewise_Training_CVPR_2016_paper.pdf)

### ENet A Deep Neural Network Architecture for Real-Time Semantic Segmentation [[paper]](https://arxiv.org/abs/1606.02147)

### Fast, Exact and Multi-scale Inference for Semantic Image Segmentation with Deep Gaussian CRFs 2016 [[paper]](https://link.springer.com/chapter/10.1007/978-3-319-46478-7_25)

### Full-Resolution Residual Networks for Semantic Segmentation in Street Scenes [[paper]](https://arxiv.org/abs/1611.08323) [[theano code]](https://github.com/TobyPDE/FRRN)

### Gaussian Conditional Random Field Network for Semantic Segmentation [[paper]](https://www.cv-foundation.org/openaccess/content_cvpr_2016/html/Vemulapalli_Gaussian_Conditional_Random_CVPR_2016_paper.html)

### Instance-aware Semantic Segmentation via Multi-task Network Cascades CVPR 2016 [[paper]](http://www.cv-foundation.org/openaccess/content_cvpr_2016/html/Dai_Instance-Aware_Semantic_Segmentation_CVPR_2016_paper.html)

### Laplacian Pyramid Reconstruction and Refinement for Semantic Segmentation ECCV 2016 [[paper]](https://link.springer.com/chapter/10.1007/978-3-319-46487-9_32) [[matconvnet code]](https://github.com/golnazghiasi/LRR)

### Multi-scale Patch Aggregation (MPA) for Simultaneous Detection and Segmentation CVPR 2016 [[paper]](http://openaccess.thecvf.com/content_cvpr_2016/html/Liu_Multi-Scale_Patch_Aggregation_CVPR_2016_paper.html)

### MultiNet Real-time Joint Semantic Reasoning for Autonomous Driving 2016 [[paper]](https://arxiv.org/abs/1612.07695)

### ParseNet - Looking Wider to See Better ICLR 2016 [[arXiv paper]](https://arxiv.org/abs/1506.04579)

### Pixel-level Encoding and Depth Layering for Instance-level Semantic Labeling 2016 [[paper]](https://arxiv.org/abs/1604.05096)

### Semantic Image Segmentation with Task-specific Edge Detection Using CNNs and a Discriminatively Trained Domain Transform [[paper]](http://www.cv-foundation.org/openaccess/content_cvpr_2016/papers/Chen_Semantic_Image_Segmentation_CVPR_2016_paper.pdf)

### The One Hundred Layers Tiramisu Fully Convolutional DenseNets for Semantic Segmentation [[paper]](https://arxiv.org/abs/1611.09326) [[Keras code]](https://github.com/0bserver07/One-Hundred-Layers-Tiramisu) [[Theano code]](https://github.com/SimJeg/FC-DenseNet)

### V-Net Fully Convolutional Neural Networks for Volumetric Medical Image Segmentation IEEE IC3DV 2016 [[paper]](http://ieeexplore.ieee.org/document/7785132/)

## 2015

### Bayesian SegNet Model Uncertainty in Deep Convolutional Encoder-Decoder Architectures for Scene Understanding [[paper]](https://arxiv.org/abs/1511.02680)

### BoxSup Exploiting Bounding Boxes to Supervise Convolutional Networks for Semantic Segmentation ICCV 2015 [[paper]](https://www.cv-foundation.org/openaccess/content_iccv_2015/papers/Dai_BoxSup_Exploiting_Bounding_ICCV_2015_paper.pdf)

### (CRFasRNN) Conditional Random Fields as Recurrent Neural Networks [[paper]](http://www.robots.ox.ac.uk/~szheng/papers/CRFasRNN.pdf)

### Feedforward Semantic Segmentation with Zoom-out Features CVPR 2015 [[paper]](https://arxiv.org/abs/1412.0774)

### Fully Connected Deep Structured Networks [[paper]](https://arxiv.org/abs/1503.02351)

### (FCN) Fully Convolutional Networks for Semantic Segmentation CVPR 2015 [[paper]](https://openaccess.thecvf.com/content_cvpr_2015/html/Long_Fully_Convolutional_Networks_2015_CVPR_paper.html) [[arXiv paper]](https://arxiv.org/abs/1411.4038)

"the first work on FCN for semantic segmentation", "PASCAL VOC 2012: 62.2 mAP"

### Hypercolumns for Object Segmentation and Fine-grained Localization [[paper]](https://www.cv-foundation.org/openaccess/content_cvpr_2015/papers/Hariharan_Hypercolumns_for_Object_2015_CVPR_paper.pdf)

### Monocular Object Instance Segmentation and Depth Ordering with CNNs ICCV 2015 [[paper]](https://ieeexplore.ieee.org/document/7410657/)

### Multi-scale Context Aggregation by Dilated Convolutions [[paper]](http://arxiv.org/abs/1511.07122)

"VOC 2012: 75.3 mAP"

### SegNet A Deep Convolutional Encoder-Decoder Architecture for Robust Semantic Pixel-wise Labelling [[paper]](https://arxiv.org/abs/1505.07293)

### Semantic Image Segmentation via Deep Parsing Network ICCV 2015 [[paper]](http://www.cv-foundation.org/openaccess/content_iccv_2015/html/Liu_Semantic_Image_Segmentation_ICCV_2015_paper.html)

### (DeepLab V1) Semantic Image Segmentation with Deep Convolutional Nets and Fully Connected CRFs ICLR 2015 [[iarXiv paper]](http://arxiv.org/abs/1412.7062)

### U-Net - Convolutional Networks for Biomedical Image Segmentation MICCAI 2015 [[paper]](https://link.springer.com/chapter/10.1007/978-3-319-24574-4_28)

### Weakly and Semi-supervised Learning of a DCNN for Semantic Image Segmentation [[paper]](http://openaccess.thecvf.com/content_iccv_2015/papers/Papandreou_Weakly-_and_Semi-Supervised_ICCV_2015_paper.pdf)

## 2014

### Material Recognition in the Wild with the Materials in Context Database [[paper]](https://arxiv.org/abs/1412.0623)

### Predicting Depth Surface Normals and Semantic Labels with a Common Multi-scale Convolutional Architecture [[paper]](http://arxiv.org/abs/1411.4734)

## 2013

### Learning Hierarchical Features for Scene Labeling [[paper]](http://yann.lecun.com/exdb/publis/pdf/farabet-pami-13.pdf)