Research map / Label-efficient and robust learning / Zero-/few-shot and meta-learning
Recognizing Part Attributes With Insufficient Data
Xiangyun Zhao, Yi Yang, Feng Zhou, Xiao Tan, Yuchen Yuan, Yingze Bao, Ying Wu
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 part-localization sharing (ablation) | CSN, 200 train imgs · CUB bill-grey | AP: 38.5% -> 42.2% | Improved |
| add pattern sharing on top of part sharing (ablation) | CSN, 200 train imgs · CUB bill-grey | AP: 42.2% -> 46.8% | Improved |
| add pattern sharing on top of part sharing (ablation) | CSN, 500 train imgs · CUB bill-black | AP: 79.4% -> 77.0% | Hurt |
| add pattern sharing on top of part sharing (ablation) | CSN, 200 train imgs · CUB bill-black | AP: 78.6% -> 76.0% | Hurt |
| add part sharing (ablation) | CSN, 500 train imgs · CUB belly-solid | AP: 83.6% -> 85.9% | Improved |
| add part sharing (ablation) | CSN, 200 train imgs · CUB belly-solid | AP: 79.2% -> 84.0% | Improved |
| increase number of sharing part attributes from 0 to 24 (ablation) | CSN · CUB bill-orange | AP: 38.6% -> 42.7% | Improved |
| add 9 sharing pattern attributes on top of 24 part attributes (ablation) | CSN · CUB bill-orange | AP: 42.7% -> 43.0% | Improved |
| add concept sharing (CSN) instead of independent branches | Baseline · SurveilA attribute 10 (umbrella) | AP: 0.5% -> 30.3% | Improved |
| add concept sharing (CSN) instead of independent branches | Baseline · SurveilA | mAP: 30.3% -> 51.2% | Improved |
| add concept sharing localization to CSN w/o share (ablation) | CSN w/o share · CelebA | attribute accuracy: 91.7% -> 91.8% | Improved |
| initialise soft part weights to all ones instead of one-hot prior (ablation) | CSN-soft · CUB-200-2011 (32 attributes) | AP: 65.1% -> 63.8% | Hurt |
Closest papers by meaning
- Joint Semantic and Latent Attribute Modelling for Cross-Class Transfer Learning (TPAMI 2017 · similarity 0.83)
- Explanatory Object Part Aggregation for Zero-Shot Learning (TPAMI 2023 · similarity 0.83)
- Objects as Context for Detecting Their Semantic Parts (CVPR 2018 · similarity 0.82)
- Semi-supervised Learning with a Teacher-student Network for Generalized Attribute Prediction (ECCV 2020 · similarity 0.82)
- Multi-Part Object Representations via Graph Structures and Co-Part Discovery (NeurIPS 2026 · similarity 0.81)
- Interpretable Image Classification via Non-parametric Part Prototype Learning (CVPR 2025 · similarity 0.81)
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.
