Research map / Detection and segmentation / Weakly supervised detection and segmentation
Max Pooling with Vision Transformers Reconciles Class and Shape in Weakly Supervised Semantic Segmentation
Simone Rossetti, Damiano Zappia, Marta Sanzari, Marco Schaerf, Fiora Pirri
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 equivariance loss L_ET with two branches (ViT-S/16) (ablation) | ViT-PCM · PASCAL VOC 2012 train | mIoU: 44.0 -> 59.2 (+15.2) | Improved |
| add equivariance loss L_ET with two branches (ViT-S/16) (ablation) | ViT-PCM · PASCAL VOC 2012 val | mIoU: 43.3 -> 56.4 (+13.1) | Improved |
| add equivariance loss L_ET with two branches (ViT-B/16) (ablation) | ViT-PCM · PASCAL VOC 2012 train | mIoU: 45.6 -> 65.1 (+19.5) | Improved |
| add equivariance loss L_ET with two branches (ViT-B/16) (ablation) | ViT-PCM · PASCAL VOC 2012 val | mIoU: 44.1 -> 62.4 (+18.3) | Improved |
| add HV-BiLSTM patch conditioning (ViT-S/16) (ablation) | ViT-PCM · PASCAL VOC 2012 train | mIoU: 59.2 -> 63.6 (+4.4) | Improved |
| add HV-BiLSTM patch conditioning (ViT-S/16) (ablation) | ViT-PCM · PASCAL VOC 2012 val | mIoU: 56.4 -> 61.8 (+5.4) | Improved |
| add HV-BiLSTM patch conditioning (ViT-B/16) (ablation) | ViT-PCM · PASCAL VOC 2012 train | mIoU: 65.1 -> 67.7 (+2.6) | Improved |
| add HV-BiLSTM patch conditioning (ViT-B/16) (ablation) | ViT-PCM · PASCAL VOC 2012 val | mIoU: 62.4 -> 66.0 (+3.6) | Improved |
| add dense CRF post-processing (ViT-S/16) (ablation) | ViT-PCM · PASCAL VOC 2012 train | mIoU: 63.6 -> 67.1 (+3.5) | Improved |
| add dense CRF post-processing (ViT-B/16) (ablation) | ViT-PCM · PASCAL VOC 2012 train | mIoU: 67.7 -> 71.4 (+3.7) | Improved |
| add dense CRF post-processing (ViT-B/16) (ablation) | ViT-PCM · PASCAL VOC 2012 val | mIoU: 66.0 -> 69.3 (+3.3) | Improved |
| larger ViT backbone, ViT-S/16 to ViT-B/16 (full model with CRF) (ablation) | ViT-PCM · PASCAL VOC 2012 val | mIoU: 64.9 -> 69.3 | Improved |
Closest papers by meaning
- Diffusion-Guided Weakly Supervised Semantic Segmentation (ECCV 2024 · similarity 0.91)
- Phase Concentration and Shortcut Suppression for Weakly Supervised Semantic Segmentation (ECCV 2024 · similarity 0.90)
- Weakly Supervised Semantic Segmentation via Progressive Confidence Region Expansion (CVPR 2025 · similarity 0.90)
- Progressive Feature Self-Reinforcement for Weakly Supervised Semantic Segmentation (AAAI 2024 · similarity 0.89)
- From SAM to CAMs: Exploring Segment Anything Model for Weakly Supervised Semantic Segmentation (CVPR 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.
