Research map / Detection and segmentation / Weakly supervised detection and segmentation
Phase Concentration and Shortcut Suppression for Weakly Supervised Semantic Segmentation
Hoyong Kwon, Jaeseok Jeong, Sung-Hoon Yoon, Kuk-Jin Yoon
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 Frequency Shortcut Suppression (FSS) (ablation) | ViT WSSS baseline (refined CAMs) · PASCAL VOC 2012 train | mIoU (%): 63.2 -> 65.4 | Improved |
| add Magnitude-mixing-based Phase Concentration (MPC) (ablation) | ViT WSSS baseline (refined CAMs) · PASCAL VOC 2012 train | mIoU (%): 63.2 -> 67.2 | Improved |
| add FSS on top of MPC (ablation) | baseline + MPC · PASCAL VOC 2012 train | mIoU (%): 67.2 -> 69.5 | Improved |
| add FSS to raw (unrefined) CAMs (ablation) | baseline · PASCAL VOC 2012 train | precision / mIoU: precision 53.2 -> 71.3; mIoU 45.3 -> 59.4 | Improved |
| add FSS (ablation) | bird class CAMs · PASCAL VOC 2012 train | precision: 17.3 -> 59.2 | Improved |
| apply MPC at layer 8 instead of late layers 10 or 11 (ablation) | MPC · PASCAL VOC 2012 train | mIoU (%): 66.4 (layer 11) -> 69.5 (layer 8) | Improved |
| apply MPC at early layers (3, 4) instead of 8 (ablation) | MPC · PASCAL VOC 2012 train | mIoU (%): 69.5 -> 68.0 (layer 3) | Hurt |
| use magnitude mixing ratio r below 0.5 (best 0.3) (ablation) | MPC · PASCAL VOC 2012 train | mIoU (%): minimum gain of 2.3%p over FSS alone | Improved |
| use ours with DeiT-S pseudo labels instead of USAGE | WSSS segmentation · PASCAL VOC 2012 val | mIoU (%): 71.9 -> 73.2 | Improved |
| use ours instead of ACR | WSSS segmentation · MS COCO 2014 val | mIoU (%): 45.3 -> 45.7 | Improved |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 2 on most shared results.
- USAGE — USAGE: A Unified Seed Area Generation Paradigm for Weakly Supervised Semantic Segmentation (ICCV 2023) · better on 5 of 5 shared results
- MCTformer — MCTformer+: Multi-Class Token Transformer for Weakly Supervised Semantic Segmentation (TPAMI 2024) · better on 1 of 1 shared result
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
- Threshold Matters in WSSS: Manipulating the Activation for the Robust and Accurate Segmentation Model Against Thresholds (CVPR 2022 · similarity 0.91)
- Progressive Feature Self-Reinforcement for Weakly Supervised Semantic Segmentation (AAAI 2024 · similarity 0.91)
- Weakly Supervised Semantic Segmentation via Progressive Confidence Region Expansion (CVPR 2025 · similarity 0.90)
- W2P: Switching from Weak Supervision to Partial Supervision for Semantic Segmentation (AAAI 2024 · similarity 0.89)
- Weakly Supervised Semantic Segmentation for Driving Scenes (AAAI 2024 · similarity 0.89)
- Class Tokens Infusion for Weakly Supervised Semantic Segmentation (CVPR 2024 · similarity 0.89)
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.
