Research map / Detection and segmentation / Weakly supervised detection and segmentation
Cyclic Guidance for Weakly Supervised Joint Detection and 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 |
|---|---|---|---|
| Add cyclic detection-segmentation guidance in both directions (ablation) | WS-JDS · PASCAL VOC 2007 test | AP: 42.0 -> 45.6 | Helped |
| Add segmentation-to-detection guidance (ablation) | WS-JDS · PASCAL VOC 2007 test | AP: 37.3 -> 42.0 | Helped |
| Add detection-to-segmentation guidance (ablation) | WS-JDS · PASCAL VOC 2007 test | AP: 37.3 -> 37.7 | No clear effect |
| Train Fast-RCNN on WS-JDS pseudo ground-truth boxes | WS-JDS · PASCAL VOC 2007 test | AP: 45.6 -> 52.5 | Helped |
| Use WS-JDS rather than Tang et al. as the detector | PASCAL VOC 2007 test · PASCAL VOC 2007 test | AP: 45.3 -> 45.6 | Helped |
| Use WS-JDS FRCNN rather than W2F | PASCAL VOC 2007 test · PASCAL VOC 2007 test | AP: 52.4 -> 52.5 | No clear effect |
| Use WS-JDS rather than W2F | PASCAL VOC 2012 test · PASCAL VOC 2012 test | mAP: 47.8 -> 39.1 | Hurt |
| Train Fast-RCNN on WS-JDS pseudo ground-truth boxes | WS-JDS · PASCAL VOC 2012 test | mAP: 39.1 -> 46.1 | Helped |
Closest papers by meaning
- Multi-Evidence Filtering and Fusion for Multi-Label Classification, Object Detection and Semantic Segmentation Based on Weakly Supervised Learning (CVPR 2018 · similarity 0.91)
- Separate and Conquer: Decoupling Co-occurrence via Decomposition and Representation for Weakly Supervised Semantic Segmentation (CVPR 2024 · similarity 0.89)
- Weakly-Supervised Semantic Segmentation by Iteratively Mining Common Object Features (CVPR 2018 · similarity 0.89)
- W2P: Switching from Weak Supervision to Partial Supervision for Semantic Segmentation (AAAI 2024 · similarity 0.87)
- Progressive Feature Self-Reinforcement for Weakly Supervised Semantic Segmentation (AAAI 2024 · similarity 0.87)
- WISH: Weakly Supervised Instance Segmentation using Heterogeneous Labels (CVPR 2025 · similarity 0.87)
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.