Research map / Label-efficient and robust learning / Recognition and long-tail
Spatial and Semantic Consistency Regularizations for Pedestrian Attribute Recognition
Jian Jia, Xiaotang Chen, Kaiqi Huang
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 spatial consistency regularization (SPAC) to the baseline (ablation) | Baseline ResNet50 · PETA | mA: 81.15 -> 84.08 | Improved |
| add spatial consistency regularization (SPAC) to the baseline (ablation) | Baseline ResNet50 · PA100K | mA: 78.53 -> 79.15 | Improved |
| add spatial consistency regularization (SPAC) to the baseline (ablation) | Baseline ResNet50 · RAP | mA: 76.09 -> 78.55 | Improved |
| add semantic consistency regularization (SEMC) alone to the baseline (ablation) | Baseline ResNet50 · PA100K | mA: 78.53 -> 78.63 | No clear effect |
| add semantic consistency regularization (SEMC) alone to the baseline (ablation) | Baseline ResNet50 · PETA | mA: 81.15 -> 82.34 | Improved |
| add SEMC on top of SPAC (ablation) | SPAC model · PA100K | mA: 79.15 -> 80.09 | Improved |
| add weighted loss to SPAC+SEMC (ablation) | SPAC+SEMC model · PA100K | mA: 80.09 -> 81.87 | Improved |
| add weighted loss to SPAC+SEMC (ablation) | SPAC+SEMC model · RAP | mA: 80.26 -> 82.77 | Improved |
| add weighted loss alone to the baseline (ablation) | Baseline ResNet50 · RAP | mA: 76.09 -> 79.46 | Improved |
| use full SPAC+SEMC+weighted loss versus baseline | Baseline ResNet50 · PETA | mA: 81.15 -> 86.52 | Improved |
| raise confidence threshold tau from 0 to 0.9 (ablation) | SSC_soft · PA100K | mA: 79.63 -> 81.87 | Improved |
| lower momentum coefficient alpha from 0.9 to 0.1 (ablation) | SSC_soft · PA100K | mA: 81.87 -> 80.89 | Hurt |
Closest papers by meaning
- Learning Disentangled Attribute Representations for Robust Pedestrian Attribute Recognition (AAAI 2022 · similarity 0.89)
- Pedestrian Attribute Recognition: A New Benchmark Dataset and a Large Language Model Augmented Framework (AAAI 2025 · similarity 0.87)
- Pedestrian Attribute Recognition as Label-balanced Multi-label Learning (ICML 2024 · similarity 0.86)
- Enhanced Visual-Semantic Interaction with Tailored Prompts for Pedestrian Attribute Recognition (CVPR 2025 · similarity 0.85)
- Selective and Orthogonal Feature Activation for Pedestrian Attribute Recognition (AAAI 2024 · similarity 0.85)
- Attribute-Guided Pedestrian Retrieval: Bridging Person Re-ID with Internal Attribute Variability (CVPR 2024 · similarity 0.83)
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.
