Research map / Detection and segmentation / Weakly supervised detection and segmentation
LCTR: On Awakening the Local Continuity of Transformer for Weakly Supervised Object Localization
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 RPAM and CDM to the transformer WSOL baseline | LCTR · CUB-200-2011 test | Top-1 localization accuracy: 71.3 -> 79.2 | Helped |
| Add RPAM and CDM to the transformer WSOL baseline | LCTR · ILSVRC validation | Top-1 localization accuracy: 53.4 -> 56.1 | Helped |
| Add RPAM to the TS-CAM baseline (ablation) | LCTR · CUB-200-2011 test | Top-1 localization accuracy: 71.3 -> 74.0 | Helped |
| Add RPAM to the TS-CAM baseline (ablation) | LCTR · ILSVRC validation | Top-1 localization accuracy: 53.4 -> 54.2 | Helped |
| Add CDM to the TS-CAM baseline (ablation) | LCTR · CUB-200-2011 test | Top-1 localization accuracy: 71.3 -> 76.0 | Helped |
| Add CDM to the TS-CAM baseline (ablation) | LCTR · ILSVRC validation | Top-1 localization accuracy: 53.4 -> 55.1 | Helped |
| Add CDM with G=4 alongside RPAM (ablation) | LCTR · CUB-200-2011 test | Top-1 localization accuracy: 74.0 -> 79.2 | Helped |
| Add CDM with G=4 alongside RPAM (ablation) | LCTR · ILSVRC validation | Top-1 localization accuracy: 54.2 -> 56.1 | Helped |
| Set CDM G to 2 instead of 4 (ablation) | LCTR · CUB-200-2011 test | Top-1 localization accuracy: 76.0 -> 75.2 | Hurt |
| Increase CDM G from 4 to 8 (ablation) | LCTR · CUB-200-2011 test | Top-1 localization accuracy: 76.0 -> 74.3 | Hurt |
| Increase CDM G from 4 to 16 (ablation) | LCTR · CUB-200-2011 test | Top-1 localization accuracy: 76.0 -> 74.1 | Hurt |
| Increase CDM G from 4 to 32 (ablation) | LCTR · CUB-200-2011 test | Top-1 localization accuracy: 76.0 -> 74.0 | Hurt |
Closest papers by meaning
- Evaluating Weakly Supervised Object Localization Methods Right (CVPR 2020 · similarity 0.91)
- Weakly Supervised Object Localization As Domain Adaption (CVPR 2022 · similarity 0.90)
- Strengthen Learning Tolerance for Weakly Supervised Object Localization (CVPR 2021 · similarity 0.90)
- Shallow Feature Matters for Weakly Supervised Object Localization (CVPR 2021 · similarity 0.89)
- Unveiling the Potential of Structure Preserving for Weakly Supervised Object Localization (CVPR 2021 · similarity 0.89)
- CAM Back Again: Large Kernel CNNs from a Weakly Supervised Object Localization Perspective (CVPR 2024 · 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.