Research map / Detection and segmentation / Weakly supervised detection and segmentation
Class Token as Proxy: Optimal Transport-assisted Proxy Learning for Weakly Supervised Semantic Segmentation
Jian Wang, Tianhong Dai, Bingfeng Zhang, Siyue Yu, Eng Gee Lim, Jimin Xiao
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| add OT-assisted proxy learning (ablation) | MCTformer+ · PASCAL VOC 2012 train | mIoU: 68.8 -> 71.5 | Improved |
| add OT-assisted proxy-patch contrastive learning (Lppc) directly on class tokens (ablation) | MCTformer+ · PASCAL VOC 2012 train | mIoU: 68.8 -> 70.7 | Improved |
| add Lppc on top of proxy learning (ablation) | OTPL · PASCAL VOC 2012 train | mIoU: 71.5 -> 73.4 | Improved |
| add CAM-based marginal constraint in OT (ablation) | OTPL proxy learning · PASCAL VOC 2012 train | mIoU: 71.0 -> 71.5 | Improved |
| select positive pairs using both CAM and OT plan instead of CAM only (ablation) | Lppc · PASCAL VOC 2012 train | mIoU: 72.5 -> 73.4 | Improved |
| select positive pairs using both CAM and OT plan instead of OT only (ablation) | Lppc · PASCAL VOC 2012 train | mIoU: 72.7 -> 73.4 | Improved |
| integrate OTPL into CLIP-ES | CLIP-ES · PASCAL VOC 2012 train | CAM mIoU: 70.8 -> 74.8 | Improved |
| integrate OTPL into CLIP-ES | CLIP-ES · PASCAL VOC 2012 train | pseudo-mask mIoU: 75.0 -> 79.2 | Improved |
| integrate OTPL into MCTformer+ | MCTformer+ · PASCAL VOC 2012 train | CAM mIoU: 68.8 -> 73.4 | Improved |
| integrate OTPL into CLIP-ES | CLIP-ES · MS COCO 2014 val | mIoU: 45.4 -> 47.6 | Improved |
| integrate OTPL into MCTformer+ | MCTformer+ · PASCAL VOC 2012 val (segmentation) | mIoU: 74.0 -> 75.6 | Improved |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.
- MCTformer+ — MCTformer+: Multi-Class Token Transformer for Weakly Supervised Semantic Segmentation (TPAMI 2024) · better on 5 of 5 shared results
Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.
Closest papers by meaning
- Class Tokens Infusion for Weakly Supervised Semantic Segmentation (CVPR 2024 · similarity 0.90)
- Class Re-Activation Maps for Weakly-Supervised Semantic Segmentation (CVPR 2022 · similarity 0.90)
- Learning Integral Objects With Intra-Class Discriminator for Weakly-Supervised Semantic Segmentation (CVPR 2020 · similarity 0.90)
- Progressive Feature Self-Reinforcement for Weakly Supervised Semantic Segmentation (AAAI 2024 · similarity 0.88)
- MoRe: Class Patch Attention Needs Regularization for Weakly Supervised Semantic Segmentation (AAAI 2025 · similarity 0.88)
- From SAM to CAMs: Exploring Segment Anything Model for Weakly Supervised Semantic Segmentation (CVPR 2024 · similarity 0.88)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
