Research map / Detection and segmentation / Weakly supervised detection and segmentation
Rethinking Class Activation Mapping for Weakly Supervised Object Localization
Wonho Bae, Junhyug Noh, Gunhee Kim
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (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 thresholded average pooling (TAP) (ablation) | Vanilla CAM VGG16 · CUB-200-2011 | Top-1 Loc: 37.05 -> 48.53 | Improved |
| add thresholded average pooling (TAP) (ablation) | Vanilla CAM VGG16 · ImageNet-1K | Top-1 Loc: 41.91 -> 45.29 | Improved |
| add thresholded average pooling (TAP) (ablation) | Vanilla CAM VGG16 · CUB-200-2011 | Top-1 Cls: 69.95 -> 74.91 | Improved |
| add negative weight clamping (NWC) (ablation) | Vanilla CAM VGG16 · CUB-200-2011 | Top-1 Loc: 37.05 -> 44.15 | Improved |
| add negative weight clamping (NWC) (ablation) | Vanilla CAM VGG16 · ImageNet-1K | Top-1 Loc: 41.91 -> 42.39 | Improved |
| add percentile as thresholding standard (PaS) (ablation) | Vanilla CAM VGG16 · CUB-200-2011 | Top-1 Loc: 37.05 -> 48.45 | Improved |
| add percentile as thresholding standard (PaS) (ablation) | Vanilla CAM VGG16 · ImageNet-1K | Top-1 Loc: 41.91 -> 44.04 | Improved |
| combine TAP, NWC and PaS (ablation) | Vanilla CAM VGG16 · CUB-200-2011 | Top-1 Loc: 37.05 -> 61.30 | Improved |
| combine TAP, NWC and PaS (ablation) | Vanilla CAM VGG16 · ImageNet-1K | Top-1 Loc: 41.91 -> 45.40 | Improved |
| add the three techniques | Vanilla CAM · ImageNet-1K | Top-1 Loc: 46.64 -> 51.96 | Improved |
| add the three techniques | Vanilla CAM GoogleNet · CUB-200-2011 | Top-1 Loc: 46.86 -> 51.05 | Improved |
| add the three techniques | HaS-32 VGG16 · CUB-200-2011 | Top-1 Loc: 49.46 -> 57.37 | Improved |
Closest papers by meaning
- Online Refinement of Low-Level Feature Based Activation Map for Weakly Supervised Object Localization (ICCV 2021 · similarity 0.95)
- Evaluating Weakly Supervised Object Localization Methods Right (CVPR 2020 · similarity 0.94)
- Evaluation for Weakly Supervised Object Localization: Protocol, Metrics, and Datasets (TPAMI 2022 · similarity 0.94)
- Normalization Matters in Weakly Supervised Object Localization (ICCV 2021 · similarity 0.94)
- Bridging the Gap Between Classification and Localization for Weakly Supervised Object Localization (CVPR 2022 · similarity 0.93)
- Background-Aware Classification Activation Map for Weakly Supervised Object Localization (TPAMI 2023 · similarity 0.93)
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.
