Research map / Label-efficient and robust learning / Recognition and long-tail
Self-similarity Driven Scale-invariant Learning for Weakly Supervised Person Search
Benzhi Wang, Yang Yang, Jinlin Wu, Guo-jun Qi, Zhen Lei
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 scale-invariant loss with multi-scale exemplar branch to baseline (ablation) | weakly supervised person search baseline · PRW | mAP: 18.8 -> 26.2 | Improved |
| add dynamic multi-label learning to baseline (ablation) | weakly supervised person search baseline · PRW | mAP: 18.8 -> 20.8 | Improved |
| add dynamic multi-label learning on top of baseline plus scale-invariant loss (ablation) | SSL · CUHK-SYSU | mAP: 86.2 -> 87.4 | Improved |
| use multiple scales instead of a single scale for exemplars (ablation) | SSL · PRW | mAP: 24.3 -> 27.1 | Improved |
| use a single fixed scale instead of original crop size (ablation) | SSL · PRW | mAP: 23.9 -> 24.3 | No clear effect |
| filter background of cropped exemplars with binary masks (ablation) | SSL · PRW | mAP: 27.1 -> 28.6 | Improved |
| use dynamic threshold for multi-label pseudo labels instead of a fixed threshold (ablation) | SSL · CUHK-SYSU | mAP: 84.2 -> 87.4 | Improved |
| use dynamic threshold instead of fixed threshold (ablation) | SSL · PRW | mAP: 29.2 -> 30.7 | Improved |
| weakly supervised SSL versus fully supervised methods | SSL · PRW | mAP: 30.7 vs 53.3 (COAT) | Hurt |
Closest papers by meaning
- Weakly Supervised Person Search With Region Siamese Networks (ICCV 2021 · similarity 0.88)
- Person Search by Multi-Scale Matching (ECCV 2018 · similarity 0.88)
- Optimizing Label Assignment for Weakly Supervised Person Search (AAAI 2025 · similarity 0.87)
- Exploring Visual Context for Weakly Supervised Person Search (AAAI 2022 · similarity 0.87)
- Learning from Synchronization: Self-Supervised Uncalibrated Multi-View Person Association in Challenging Scenes (CVPR 2025 · similarity 0.86)
- Divide and Conquer: Hybrid Pre-training for Person Search (AAAI 2024 · similarity 0.85)
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.
