Research map / Detection and segmentation / Weakly supervised detection and segmentation
Railroad Is Not a Train: Saliency As Pseudo-Pixel Supervision for Weakly Supervised Semantic Segmentation
Check 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 |
|---|---|---|---|
| combine saliency-map pseudo-pixel feedback with image-level classification supervision | EPS · PASCAL VOC 2012 val | mIoU: 71.0 | Helped |
| combine saliency-map pseudo-pixel feedback with image-level classification supervision | EPS · MS COCO 2014 val | mIoU: 35.7 | Helped |
| use adaptive overlap-based map selection instead of no map selection (ablation) | EPS pseudo-mask generation · PASCAL VOC 2012 train | mIoU: 66.1 -> 69.4 | Helped |
| use adaptive overlap-based map selection instead of naive map selection (ablation) | EPS pseudo-mask generation · PASCAL VOC 2012 train | mIoU: 66.5 -> 69.4 | Helped |
| use adaptive overlap-based map selection instead of manually pre-defined background classes (ablation) | EPS pseudo-mask generation · PASCAL VOC 2012 train | mIoU: 67.9 -> 69.4 | Helped |
| replace PFAN with DSS saliency maps (ablation) | EPS · PASCAL VOC 2012 val | mIoU: 71.0 -> 70.0 | Hurt |
| replace PFAN with USPS unsupervised saliency maps (ablation) | EPS · PASCAL VOC 2012 val | mIoU: 71.0 -> 68.8 | Hurt |
| replace PFAN with USPS unsupervised saliency maps (ablation) | EPS · PASCAL VOC 2012 test | mIoU: 71.8 -> 69.9 | Hurt |
Closest papers by meaning
- Joint Semantic Mining for Weakly Supervised RGB-D Salient Object Detection (NeurIPS 2021 · similarity 0.91)
- Exploiting Saliency for Object Segmentation From Image Level Labels (CVPR 2017 · similarity 0.91)
- Learning Saliency-Free Model with Generic Features for Weakly-Supervised Semantic Segmentation (AAAI 2020 · similarity 0.91)
- Progressive Feature Self-Reinforcement for Weakly Supervised Semantic Segmentation (AAAI 2024 · similarity 0.91)
- Combining Bottom-Up, Top-Down, and Smoothness Cues for Weakly Supervised Image Segmentation (CVPR 2017 · similarity 0.91)
- W2P: Switching from Weak Supervision to Partial Supervision for Semantic Segmentation (AAAI 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.