1 前言
本文盘点了CVPR 2022 目前为止的2D图像分割相关论文，包含语义分割和实例分割，总计22篇论文，值得学习。
2 语义分割
2.1 强监督
(1) ReSTR: Convolution-free Referring Image Segmentation Using Transformers
论文：https://arxiv.org/pdf/2203.16768.pdf
代码：暂无
(2) Bending Reality: Distortion-aware Transformers for Adapting to Panoramic Semantic Segmentation
论文：https://arxiv.org/pdf/2203.16768.pdf
代码：https://github.com/jamycheung/Trans4PASS
(3) Deep Hierarchical Semantic Segmentation
论文：https://arxiv.org/pdf/2203.14335.pdf
代码：https://github.com/0liliulei/HieraSeg
(4) Semantic Segmentation by Early Region Proxy
论文：https://arxiv.org/pdf/2203.14043.pdf
代码：https://github.com/YiFZhang/RegionProxy
(5) SimT: Handling Open-set Noise for Domain Adaptive Semantic Segmentation
论文：https://arxiv.org/pdf/2203.15202.pdf
代码：https://github.com/CityU-AIM-Group/SimT
(6) Rethinking Semantic Segmentation: A Prototype View
论文：https://arxiv.org/pdf/2203.15102.pdf
代码：https://github.com/tfzhou/ProtoSeg
2.2 弱监督
(1) Class Re-Activation Maps for Weakly-Supervised Semantic Segmentation
(弱监督语义分割的类重新激活图)
论文：https://arxiv.org/pdf/2203.00962.pdf
代码：https://github.com/zhaozhengChen/ReCAM
(2) Multi-class Token Transformer for Weakly Supervised Semantic Segmentation
论文：https://arxiv.org/pdf/2203.02891.pdf
代码：https://github.com/xulianuwa/MCTformer
(3) Learning Affinity from Attention: End-to-End Weakly-Supervised Semantic Segmentation with Transformers
论文：https://arxiv.org/pdf/2203.02664.pdf
代码：https://github.com/rulixiang/afa
(4) Self-supervised Image-specific Prototype Exploration for Weakly Supervised Semantic Segmentation
论文：https://arxiv.org/pdf/2203.02909.pdf
代码： https://github.com/chenqi1126/SIPE
(5) Cross Language Image Matching for Weakly Supervised Semantic Segmentation
论文：https://arxiv.org/pdf/2203.02668.pdf
代码： https://github.com/CVISZU/CLIMS
(6) Weakly Supervised Semantic Segmentation using Out-of-Distribution Data
论文：https://arxiv.org/pdf/2203.03860.pdf
代码：https://github.com/naver-ai/w-ood
(7) Threshold Matters in WSSS: Manipulating the Activation for the Robust and Accurate Segmentation Model Against Thresholds
论文：https://arxiv.org/pdf/2203.16045.pdf
代码：https://github.com/gaviotas/AMN
2.3 半监督
(1) ST++: Make Self-training Work Better for Semi-supervised Semantic Segmentation
论文：https://arxiv.org/pdf/2106.05095.pdf
代码：https://github.com/LiheYoung/ST-PlusPlus
(2) Semi-Supervised Semantic Segmentation Using Unreliable Pseudo-Labels
论文：https://arxiv.org/pdf/2203.03884.pdf
代码：https://github.com/Haochen-Wang409/U2PL
2.4 无监督
(1) GroupViT: Semantic Segmentation Emerges from Text Supervision
论文：https://arxiv.org/pdf/2202.11094.pdf
代码： https://jerryxu.net/GroupViT
3 实例分割
3.1 强监督
(1) BoxeR: Box-Attention for 2D and 3D Transformers
论文：https://arxiv.org/pdf/2111.13087.pdf
代码：https://github.com/kienduynguyen/BoxeR.
(2) E2EC: An End-to-End Contour-based Method for High-Quality High-Speed Instance Segmentation
论文：https://arxiv.org/pdf/2203.04074.pdf
代码：https://github.com/zhang-tao-whu/e2ec.
(3) Sparse Instance Activation for Real-Time Instance Segmentation
论文：https://arxiv.org/pdf/2203.12827.pdf
代码：https://github.com/hustvl/SparseInst
(4) SharpContour: A Contour-based Boundary Refinement Approach for Efficient and Accurate Instance Segmentation
论文：https://arxiv.org/pdf/2203.13312.pdf
代码：暂无文章来源：https://www.toymoban.com/news/detail-518292.html
3.2 半监督
(1) Noisy Boundaries: Lemon or Lemonade for Semi-supervised Instance Segmentation?
论文：https://arxiv.org/pdf/2203.13427.pdf
代码：https://github.com/zhenyuw16/noisyboundaries
3.3 无监督
(1) FreeSOLO: Learning to Segment Objects without Annotations
论文：https://arxiv.org/pdf/2202.12181.pdf
代码：暂无
文章来源地址https://www.toymoban.com/news/detail-518292.html
到了这里，关于CVPR 2022: 图像分割论文大盘点的文章就介绍完了。如果您还想了解更多内容，请在右上角搜索TOY模板网以前的文章或继续浏览下面的相关文章，希望大家以后多多支持TOY模板网！
