paper-with-me

Papers

Token Contrast for Weakly-Supervised Semantic Segmentation

2023-03-02 · CVPR 2023 1 · Lixiang Ru, Heliang Zheng, Yibing Zhan, Bo Du

Weakly-Supervised Semantic Segmentation (WSSS) using image-level labels typically utilizes Class Activation Map (CAM) to generate the pseudo labels. Limited by the local structure perception of CNN, CAM usually cannot identify the integral object regions. Though the recent Vision Transformer (ViT) can remedy this flaw, we observe it also brings the over-smoothing issue, \ie, the final patch tokens incline to be uniform. In this work, we propose Token Contrast (ToCo) to address this issue and further explore the virtue of ViT for WSSS. Firstly, motivated by the observation that intermediate layers in ViT can still retain semantic diversity, we designed a Patch Token Contrast module (PTC). PTC supervises the final patch tokens with the pseudo token relations derived from intermediate layers, allowing them to align the semantic regions and thus yield more accurate CAM. Secondly, to further differentiate the low-confidence regions in CAM, we devised a Class Token Contrast module (CTC) inspired by the fact that class tokens in ViT can capture high-level semantics. CTC facilitates the representation consistency between uncertain local regions and global objects by contrasting their class tokens. Experiments on the PASCAL VOC and MS COCO datasets show the proposed ToCo can remarkably surpass other single-stage competitors and achieve comparable performance with state-of-the-art multi-stage methods. Code is available at https://github.com/rulixiang/ToCo.

📄 PDF Abstract BibTeX arXiv:2303.01267

Code (1)

rulixiang/toco 공식 구현 pytorch

Tasks

Semantic SegmentationWeakly supervised Semantic SegmentationWeakly-Supervised Semantic Segmentation

Methods 이 논문이 사용한 방법론

Attention 설명 없음
Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.
Absolute Position Encodings Absolute Position Encodings are a type of position embeddings for [Transformer-based models] where positional encodings are…
Label Smoothing Label Smoothing is a regularization technique that introduces noise for the labels. This accounts for the fact that datasets may have mistakes in them, so maximizing the…
Softmax The Softmax output function transforms a previous layer's output into a vector of probabilities. It is commonly used for multiclass classification. Given an input vector $x$…
Adam 설명 없음
Layer Normalization Unlike batch normalization, Layer Normalization directly estimates the normalization statistics from the summed inputs…
Residual Connection 설명 없음

Similar Papers 제목 키워드 기반

Masked Collaborative Contrast for Weakly Supervised Semantic Segmentation

2023-05-15 · Fangwen Wu, Jingxuan He, Yufei Yin, Yanbin Hao 외

This study introduces an efficacious approach, Masked Collaborative Contrast (MCC), to highlight semantic regions in weakly supervised semantic segmentation. MCC adroitly draws inspiration from masked image modeling and …

Contrastive LearningSemantic SegmentationWeakly supervised Semantic SegmentationWeakly-Supervised Semantic Segmentation

Multi-Label Prototype Visual Spatial Search for Weakly Supervised Semantic Segmentation

2025-01-01 · CVPR 2025 1 · Songsong Duan, Xi Yang, Nannan Wang

Existing Weakly Supervised Semantic Segmentation (WSSS) relies on the CNN-based Class Activation Map (CAM) and Transformer-based self-attention map to generate class-specific masks for semantic segmentation. However,…

Semantic SegmentationWeakly supervised Semantic SegmentationWeakly-Supervised Semantic Segmentation

Class Tokens Infusion for Weakly Supervised Semantic Segmentation

2024-01-01 · CVPR 2024 1 · Sung-Hoon Yoon, Hoyong Kwon, Hyeonseong Kim, Kuk-Jin Yoon

Weakly Supervised Semantic Segmentation (WSSS) relies on Class Activation Maps (CAMs) to extract spatial information from image-level labels. With the success of Vision Transformer (ViT) the migration of ViT is activ…

Semantic SegmentationWeakly supervised Semantic SegmentationWeakly-Supervised Semantic Segmentation

Weakly- and Semi-Supervised Panoptic Segmentation

2018-08-10 · ECCV 2018 9 · Qizhu Li, Anurag Arnab, Philip H. S. Torr

We present a weakly supervised model that jointly performs both semantic- and instance-segmentation -- a particularly relevant problem given the substantial cost of obtaining pixel-perfect annotation for these tasks. In …

Instance SegmentationPanoptic SegmentationSegmentationSemantic Segmentation+3

Weakly-supervised Semantic Segmentation via Dual-stream Contrastive Learning of Cross-image Contextual Information

2024-05-08 · Qi Lai, Chi-Man Vong

Weakly supervised semantic segmentation (WSSS) aims at learning a semantic segmentation model with only image-level tags. Despite intensive research on deep learning approaches over a decade, there is still a significant…

Contrastive LearningSegmentationSemantic SegmentationWeakly supervised Semantic Segmentation+1