Research map / Detection and segmentation / Weakly supervised detection and segmentation
Learning Pixel-Level Semantic Affinity With Image-Level Supervision for Weakly Supervised Semantic Segmentation
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (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 AffinityNet random walk to CAMs (ablation) | CAM label synthesis · PASCAL VOC 2012 train synthesized labels | mIoU: 48.0 -> 58.1 | Helped |
| Add dCRF refinement after random walk (ablation) | CAM+RW label synthesis · PASCAL VOC 2012 train synthesized labels | mIoU: 58.1 -> 59.7 | Helped |
| Add AffinityNet random walk to CAMs (ablation) | CAM label synthesis · PASCAL VOC 2012 val synthesized labels | mIoU: 46.8 -> 57.0 | Helped |
| Add dCRF refinement after random walk (ablation) | CAM+RW label synthesis · PASCAL VOC 2012 val synthesized labels | mIoU: 57.0 -> 58.7 | Helped |
| Train a segmentation network using synthesized labels instead of using the label map directly (ablation) | Ours-ResNet38 · PASCAL VOC 2012 val | mIoU: 58.7 -> 61.7 | Helped |
| Use ResNet38 rather than DeepLab as the segmentation model backbone | Proposed segmentation pipeline · PASCAL VOC 2012 val | mIoU: 58.4 -> 61.7 | Helped |
| Use ResNet38 rather than DeepLab as the segmentation model backbone | Proposed segmentation pipeline · PASCAL VOC 2012 test | mIoU: 60.5 -> 63.7 | Helped |
| Apply multi-scale and horizontal-flip test-time augmentation | Ours-ResNet38 · PASCAL VOC 2012 val | mIoU: less than 2% in mIoU | Helped |
Closest papers by meaning
- Learning Affinity From Attention: End-to-End Weakly-Supervised Semantic Segmentation With Transformers (CVPR 2022 · similarity 0.93)
- CIAN: Cross-Image Affinity Net for Weakly Supervised Semantic Segmentation (AAAI 2020 · similarity 0.92)
- Combining Bottom-Up, Top-Down, and Smoothness Cues for Weakly Supervised Image Segmentation (CVPR 2017 · similarity 0.91)
- Label-efficient Segmentation via Affinity Propagation (NeurIPS 2023 · similarity 0.91)
- Weakly-Supervised Semantic Segmentation Network With Deep Seeded Region Growing (CVPR 2018 · similarity 0.91)
- Progressive Feature Self-Reinforcement for Weakly Supervised Semantic Segmentation (AAAI 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.