Research map / Label-efficient and robust learning / Recognition and long-tail
Hierarchical Feature Embedding for Attribute Recognition
Jie Yang, Jiarou Fan, Yiru Wang, Yige Wang, Weihao Gan, Lin Liu, Wei Wu
Check 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 |
|---|---|---|---|
| Use hierarchical attribute and ID feature embedding with HFE loss | Attribute recognition · Market 1501 attribute dataset | mean accuracy: 91.27 -> 92.90 | Improved |
| Use hierarchical attribute and ID feature embedding with HFE loss | Attribute recognition · Duke attribute dataset | mean accuracy: 90.35 -> 91.77 | Improved |
| Use HFE for face attribute recognition | DeepID2 · CelebA | accuracy: 91.81 -> 92.17 | Improved |
| Add inter-class triplet loss to CE (ablation) | Attribute recognition · Market 1501 attribute dataset | mean accuracy: 88.82 -> 90.83 | Improved |
| Add intra-class ID triplet loss to CE (ablation) | Attribute recognition · Market 1501 attribute dataset | mean accuracy: 88.82 -> 91.27 | Improved |
| Combine inter-class and intra-class triplet losses (ablation) | Attribute recognition · Market 1501 attribute dataset | mean accuracy: 90.83 -> 92.44 | Improved |
| Add absolute boundary regularization (ablation) | Inter-class and intra-class triplet losses · Market 1501 attribute dataset | mean accuracy: 92.44 -> 92.73 | Improved |
| Replace fixed HFE loss weight with dynamic weight (ablation) | HFE · Market 1501 attribute dataset | mean accuracy: 92.73 -> 92.90 | Improved |
| Replace intra-class triplet loss with pairwise ID compactness loss (ablation) | Inter-class and intra-class feature embedding · Market 1501 attribute dataset | mean accuracy: 92.44 -> 92.30 | Hurt |
Closest papers by meaning
- Pedestrian Attribute Recognition: A New Benchmark Dataset and a Large Language Model Augmented Framework (AAAI 2025 · similarity 0.87)
- Attributes Shape the Embedding Space of Face Recognition Models (ICML 2025 · similarity 0.86)
- Improving Pedestrian Attribute Recognition With Weakly-Supervised Multi-Scale Attribute-Specific Localization (ICCV 2019 · similarity 0.85)
- Selective and Orthogonal Feature Activation for Pedestrian Attribute Recognition (AAAI 2024 · similarity 0.85)
- Learning Disentangled Attribute Representations for Robust Pedestrian Attribute Recognition (AAAI 2022 · similarity 0.85)
- Pedestrian Attribute Recognition as Label-balanced Multi-label Learning (ICML 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.
