Research map / Detection and segmentation / Weakly supervised detection and segmentation
Weakly Supervised Object Localization via Transformer with Implicit Spatial Calibration
Haotian Bai, Ruimao Zhang, Jiong Wang, Xiang Wan
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 SCM (dropped at inference) to TS-CAM | TS-CAM (Deit-S) · CUB-200-2011 | GT-Known: 87.7 -> 96.6 | Improved |
| add SCM (dropped at inference) to TS-CAM | TS-CAM (Deit-S) · CUB-200-2011 | Loc Acc Top-1: 71.3 -> 76.4 | Improved |
| add SCM (dropped at inference) to TS-CAM | TS-CAM (Deit-S) · CUB-200-2011 | Cls Acc Top-1: 80.3 -> 78.5 | Hurt |
| add SCM to TS-CAM | TS-CAM (Deit-S) · ILSVRC2012 val | GT-Known: 67.6 -> 68.8 | Improved |
| add SCM to TS-CAM | TS-CAM (Deit-S) · ILSVRC2012 val | Loc Acc Top-1: 53.4 -> 56.1 | Improved |
| add SCM to TS-CAM | TS-CAM (Deit-S) · CUBV2 (held-out) | MaxboxAccV2: 79.6 -> 89.9 | Improved |
| add SCM to TS-CAM | TS-CAM (Deit-S) · CUBV2 (held-out) | MaxboxAccV1: 88.9 -> 96.6 | Improved |
| use SCM with ViT backbone | ViT · CUB-200-2011 | GT-Known: 91.8 | Improved |
| use SCM with Conformer backbone | Conformer · CUB-200-2011 | GT-Known: 96.1 | Improved |
| stack more activation diffusion blocks (ablation) | SCM · CUB-200-2011 | GT-Known | Mixed |
| use larger Deit backbones instead of Deit-small (ablation) | SCM · CUB-200-2011 | GT-Known | Hurt |
| use Newton-Schulz iteration p=4 instead of other iteration counts (ablation) | SCM · CUB-200-2011 | GT-Known | Improved |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 2 on most shared results.
- TS-CAM — TS-CAM: Token Semantic Coupled Attention Map for Weakly Supervised Object Localization (ICCV 2021) · better on 10 of 12 shared results
- LCTR — LCTR: On Awakening the Local Continuity of Transformer for Weakly Supervised Object Localization (AAAI 2022) · better on 2 of 4 shared results
Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.
Closest papers by meaning
- 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)
- Cross-token Guidance Transformer for Weakly Supervised Object Localization (ECCV 2026 · similarity 0.94)
- Spatial-Aware Token for Weakly Supervised Object Localization (ICCV 2023 · similarity 0.94)
- CLIP-Driven Transformer for Weakly Supervised Object Localization (TPAMI 2025 · similarity 0.93)
- Category-aware Allocation Transformer for Weakly Supervised Object Localization (ICCV 2023 · similarity 0.92)
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.
