Research map / Detection and segmentation / Weakly supervised detection and segmentation
Strengthen Learning Tolerance for Weakly Supervised Object Localization
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 |
|---|---|---|---|
| Use SLT-Net instead of PSOL | VGG16 localization on CUB · CUB | Top-1 LOC: 66.3 -> 67.8 | Helped |
| Use SLT-Net instead of PSOL | InceptionV3 localization · ILSVRC2012 | Top-1 LOC: 53.1 -> 55.7 | Helped |
| Use SLT-Net instead of the strongest listed baseline | InceptionV3 localization · ILSVRC2012 | GT-known LOC: 68.5 -> 67.6 | Hurt |
| Use a lower learning rate and fewer training iterations (ablation) | CAM localizer · CUB | GT-known LOC: 58.0 -> 74.3 | Helped |
| Use a lower learning rate and fewer training iterations (ablation) | CAM localizer · ILSVRC2012 | GT-known LOC: 59.0 -> 60.1 | Helped |
| Add semantic-mistake-tolerant loss (ablation) | New Optimization localizer · CUB | GT-known LOC: 74.3 -> 75.7 | Helped |
| Add semantic-mistake-tolerant loss (ablation) | New Optimization localizer · ILSVRC2012 | GT-known LOC: 60.1 -> 60.5 | Helped |
| Average CAMs from the top-K predicted categories (ablation) | Semantic-tolerant localizer · CUB | GT-known LOC: 75.7 -> 78.9 | Helped |
| Average CAMs from the top-K predicted categories (ablation) | Semantic-tolerant localizer · ILSVRC2012 | GT-known LOC: 60.5 -> 61.2 | Helped |
| Add visual-stimulus-tolerance loss (ablation) | Semantic-tolerant localizer with top-K ACAM · CUB | GT-known LOC: 78.9 -> 81.3 | Helped |
| Add visual-stimulus-tolerance loss (ablation) | Semantic-tolerant localizer with top-K ACAM · ILSVRC2012 | GT-known LOC: 61.2 -> 62.7 | Helped |
| Combine semantic tolerance, top-K ACAM, and visual-stimulus tolerance (ablation) | VGG16 localizer · CUB | GT-known LOC: 81.3 -> 85.6 | Helped |
Closest papers by meaning
- Evaluating Weakly Supervised Object Localization Methods Right (CVPR 2020 · similarity 0.92)
- Weakly Supervised Object Localization As Domain Adaption (CVPR 2022 · similarity 0.91)
- LCTR: On Awakening the Local Continuity of Transformer for Weakly Supervised Object Localization (AAAI 2022 · similarity 0.90)
- Rethinking the Route Towards Weakly Supervised Object Localization (CVPR 2020 · similarity 0.90)
- Learning to Localize Objects with Noisy Labeled Instances (AAAI 2019 · similarity 0.89)
- Background Activation Suppression for Weakly Supervised Object Localization (CVPR 2022 · 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.