Research map / Label-efficient and robust learning / Zero-/few-shot and meta-learning
A Conditional Probability Framework for Compositional Zero-shot Learning
Peng Wu, Qiuxia Lai, Hao Fang, Guo-Sen Xie, Yilong Yin, Xiankai Lu, Wenguan Wang
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 text-enhanced object learning (TEO) (ablation) | CPF · C-GQA closed-world | AUC: 7.6 -> 8.2 | Improved |
| add object-guided attribute learning (OGA) on top of TEO (ablation) | CPF · C-GQA closed-world | AUC: 6.9 -> 7.6 | Improved |
| add TEO (ablation) | CPF · C-GQA open-world | AUC: 1.79 -> 2.10 | Improved |
| add OGA on top of TEO (ablation) | CPF · C-GQA open-world | AUC: 1.69 -> 1.79 | Improved |
| add TEO (ablation) | CPF · C-GQA closed-world | Seen accuracy: 39.6 -> 39.6 | No clear effect |
| use cross-attention instead of averaging for attribute guidance (Eq. 2) (ablation) | CPF · C-GQA closed-world | AUC: 7.8 -> 8.2 | Improved |
| use cross-attention instead of averaging (Eq. 4) (ablation) | CPF · C-GQA closed-world | AUC: 7.1 -> 8.2 | Improved |
| use cross-attention instead of averaging (Eq. 2) (ablation) | CPF · C-GQA open-world | AUC: 1.91 -> 2.10 | Improved |
| add shallow-level features to deep-level visual embeddings (ablation) | CPF · C-GQA closed-world | AUC: 6.7 -> 8.2 | Improved |
| add shallow-level features to deep-level visual embeddings (ablation) | CPF · C-GQA open-world | AUC: 1.58 -> 2.10 | Improved |
| condition on object visual embedding instead of attribute text embedding for attribute guidance (ablation) | CPF · C-GQA closed-world | AUC: 7.6 -> 8.2 | Improved |
| condition on object visual embedding instead of object text embedding (ablation) | CPF · C-GQA closed-world | AUC: 7.7 -> 8.2 | Improved |
Closest papers by meaning
- Context-based and Diversity-driven Specificity in Compositional Zero-Shot Learning (CVPR 2024 · similarity 0.93)
- A Dynamic Learning Method towards Realistic Compositional Zero-Shot Learning (AAAI 2024 · similarity 0.92)
- Beyond Seen Primitive Concepts and Attribute-Object Compositional Learning (CVPR 2024 · similarity 0.92)
- Revealing the Proximate Long-Tail Distribution in Compositional Zero-Shot Learning (AAAI 2024 · similarity 0.91)
- Retrieval-Augmented Primitive Representations for Compositional Zero-Shot Learning (AAAI 2024 · similarity 0.91)
- TOMCAT: Test-time Comprehensive Knowledge Accumulation for Compositional Zero-Shot Learning (NeurIPS 2025 · similarity 0.89)
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.
