作者:CV Daily | 编辑:Amusi
Date:2020-09-25
来源:计算机视觉Daily微信公众号(系投稿)
原文:ECCV 2020 语义分割论文大盘点(38篇论文)
距离ECCV 2020 会议结束有段时间了,但其中的论文大多是目前的SOTA,所以非常值得大家花时间阅读学习!
计算机视觉Daily将正式系列整理 ECCV 2020的大盘点工作,本文为第二篇:语义分割方向。第一篇是目标检测系列,详见:ECCV 2020 目标检测论文大盘点(49篇论文)
本文主要包含:一般的2D语义分割、弱监督、域自适应语义分割等方向。论文PDF已打包好,在公众号后台回复:ECCV2020语义分割,即可下载这38篇论文。
Object-Contextual Representations for Semantic Segmentation
Intra-class Feature Variation Distillation for Semantic Segmentation
Class-wise Dynamic Graph Convolution for Semantic Segmentation
Tensor Low-Rank Reconstruction for Semantic Segmentation
Improving Semantic Segmentation via Decoupled Body and Edge Supervision
Learning to Predict Context-adaptive Convolution for Semantic Segmentation
EfficientFCN: Holistically-guided Decoding for Semantic Segmentation
SNE-RoadSeg: Incorporating Surface Normal Information into Semantic Segmentation for Accurate Freespace Detection
Semantic Flow for Fast and Accurate Scene Parsing
Mining Cross-Image Semantics for Weakly Supervised Semantic Segmentation
Semi-supervised Semantic Segmentation via Strong-weak Dual-branch Network
Negative Pseudo Labeling using Class Proportion for Semantic Segmentation in Pathology
Employing Multi-Estimations for Weakly-Supervised Semantic Segmentation
Splitting vs. Merging: Mining Object Regions with Discrepancy and Intersection Loss for Weakly Supervised Semantic Segmentation
Weakly Supervised Semantic Segmentation with Boundary Exploration
Regularized Loss for Weakly Supervised Single Class Semantic Segmentation
Naive-Student: Leveraging Semi-Supervised Learning in Video Sequences for Urban Scene Segmentation
Semi-Supervised Segmentation based on Error-Correcting Supervision
Unsupervised Domain Adaptation for Semantic Segmentation of NIR Images through Generative Latent Search
Domain Adaptive Semantic Segmentation Using Weak Labels
Content-Consistent Matching for Domain Adaptive Semantic Segmentation
Classes Matter: A Fine-grained Adversarial Approach to Cross-domain Semantic Segmentation
Contextual-Relation Consistent Domain Adaptation for Semantic Segmentation
Learning from Scale-Invariant Examples for Domain Adaptation in Semantic Segmentation
Label-Driven Reconstruction for Domain Adaptation in Semantic Segmentation
作者单位:德克萨斯大学阿灵顿分校
论文:https://www.ecva.net/papers/eccv_2020/papers_ECCV/html/5818_ECCV_2020_paper.php
代码:暂无
中文解读:暂无
Prototype Mixture Models for Few-shot Semantic Segmentation
Part-aware Prototype Network for Few-shot Semantic Segmentation
Few-Shot Semantic Segmentation with Democratic Attention Networks
作者单位:北航, 阿里巴巴优酷, IIAI等
论文:https://www.ecva.net/papers/eccv_2020/papers_ECCV/html/2042_ECCV_2020_paper.php
代码:暂无
中文解读:暂无
Indirect Local Attacks for Context-aware Semantic Segmentation Networks
Segmentations-Leak: Membership Inference Attacks and Defenses in Semantic Image Segmentation
Bi-directional Cross-Modality Feature Propagation with Separation-and-Aggregation Gate for RGB-D Semantic Segmentation
作者单位:北京大学, 商汤科技, 香港中文大学
论文:https://www.ecva.net/papers/eccv_2020/papers_ECCV/html/1399_ECCV_2020_paper.php
代码:https://github.com/charlesCXK/RGBD_Semantic_Segmentation_PyTorch
中文解读:暂无
Synthesize then Compare: Detecting Failures and Anomalies for Semantic Segmentation
GMNet: Graph Matching Network for Large Scale Part Semantic Segmentation in the Wild
作者单位:帕多瓦大学
论文:https://www.ecva.net/papers/eccv_2020/papers_ECCV/html/598_ECCV_2020_paper.php
代码:https://github.com/LTTM/GMNet
中文解读:暂无
Increasing the Robustness of Semantic Segmentation Models with Painting-by-Numbers
作者单位:罗伯特·博世公司, 海德堡大学
论文:https://www.ecva.net/papers/eccv_2020/papers_ECCV/html/1097_ECCV_2020_paper.php
代码:暂无
中文解读:暂无
SideInfNet: A Deep Neural Network for Semi-Automatic Semantic Segmentation with Side Information
作者单位:新加坡科技设计大学, 迪肯大学, 香港科技大学
论文:https://www.ecva.net/papers/eccv_2020/papers_ECCV/html/4524_ECCV_2020_paper.php
代码:暂无
中文解读:暂无
Attend and Segment: Attention Guided Active Semantic Segmentation
SegFix: Model-Agnostic Boundary Refinement for Segmentation
Efficient Semantic Video Segmentation with Per-frame Inference
上述38篇论文的PDF已全部打包好,在计算机视觉Daily公众号后台回复:ECCV2020语义分割,即可下载访问
欢迎关注计算机视觉Daily