Research map / Detection and segmentation / Weakly supervised detection and segmentation
Erasing Integrated Learning: A Simple Yet Effective Approach 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 |
|---|---|---|---|
| integrate erased and unerased feature streams with shared weights | VGG-EIL · CUB-200-2011 | Top-1 Loc (%): 44.15 -> 56.21 | Helped |
| add a second EIL module at pool3 alongside pool4 (ablation) | VGG-EIL · CUB-200-2011 | Top-1 Loc: 55.44 -> 57.46 | Helped |
| place EIL at pool4 rather than pool3 (ablation) | VGG-EIL · CUB-200-2011 | Top-1 Loc (%): 51.06 -> 55.44 | Helped |
| place EIL at pool4 rather than conv5-3 (ablation) | VGG-EIL · CUB-200-2011 | Top-1 Loc (%): 46.77 -> 55.44 | Helped |
| insert a second EIL in the erased branch (MEIL II) (ablation) | VGG-MEIL · CUB-200-2011 | Top-1 Loc: null | Hurt |
| increase the erased-loss weight σ from 1 to 2 at γ=0.7 (ablation) | VGG-EIL · CUB-200-2011 | Top-1 Loc (%): 55.44 -> 56.21 | Helped |
| vary the erasing threshold γ (ablation) | VGG-EIL · CUB-200-2011 | Top-1 Loc (%): σ=1: 52.41 / 66.97, 55.44 / 72.99, 51.41 / 72.20 | Mixed |
| use MEIL on InceptionV3 rather than CAM | InceptionV3 · ILSVRC 2016 | Top-1 Loc (%): 46.29 -> 49.48 | Helped |
Closest papers by meaning
- Adversarial Complementary Learning for Weakly Supervised Object Localization (CVPR 2018 · similarity 0.92)
- Object Region Mining With Adversarial Erasing: A Simple Classification to Semantic Segmentation Approach (CVPR 2017 · similarity 0.89)
- Human-Like Delicate Region Erasing Strategy for Weakly Supervised Detection (AAAI 2019 · similarity 0.89)
- Bridging the Gap Between Classification and Localization for Weakly Supervised Object Localization (CVPR 2022 · similarity 0.88)
- Unveiling the Potential of Structure Preserving for Weakly Supervised Object Localization (CVPR 2021 · similarity 0.88)
- Evaluating Weakly Supervised Object Localization Methods Right (CVPR 2020 · 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.