Research map / Vision-language and multimodal / CLIP and zero-shot
Learning Visual Proxy for Compositional Zero-Shot Learning
Shiyu Zhang, Cheng Yan, Yang Liu, Chenchen Jing, Lei Zhou, Wenjun 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 visual proxy alongside text prototype (ablation) | VP-CMJL · UT-Zappos closed-world | AUC: 37.8 -> 47.9 | Improved |
| add visual proxy alongside text prototype (ablation) | VP-CMJL · MIT-States closed-world | AUC: 20.8 -> 23.3 | Improved |
| add text prototype alongside visual proxy (ablation) | VP-CMJL · UT-Zappos closed-world | AUC: 42.1 -> 47.9 | Improved |
| add text prototype alongside visual proxy (ablation) | VP-CMJL · MIT-States closed-world | AUC: 20.7 -> 23.3 | Improved |
| keep visual proxy branch at inference (ablation) | VP-CMJL · UT-Zappos closed-world | AUC: 44.2 -> 47.9 | Improved |
| keep text prototype branch at inference (ablation) | VP-CMJL · MIT-States closed-world | AUC: 20.4 -> 23.3 | Improved |
| keep visual proxy branch at inference (ablation) | VP-CMJL · MIT-States closed-world | AUC: 23.0 -> 23.3 | No clear effect |
| use CA for text prototype and MLP for visual proxy decoupling instead of CA/CA (ablation) | VP-CMJL · UT-Zappos closed-world | AUC: 42.0 -> 47.9 | Improved |
| use CA/MLP instead of MLP/MLP decoupling (ablation) | VP-CMJL · MIT-States closed-world | AUC: 21.8 -> 23.3 | Improved |
| use CA/MLP instead of MLP/CA decoupling (ablation) | VP-CMJL · UT-Zappos closed-world | AUC: 44.2 -> 47.9 | Improved |
| use VP-CMJL instead of Troika | VP-CMJL · C-GQA closed-world | AUC: 12.4 -> 16.3 | Improved |
| use VP-CMJL instead of CDS-CZSL | VP-CMJL · MIT-States open-world | AUC: 8.5 -> 8.3 | Hurt |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.
- Troika — Troika: Multi-Path Cross-Modal Traction for Compositional Zero-Shot Learning (CVPR 2024) · better on 6 of 6 shared results
Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.
Closest papers by meaning
- 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)
- Troika: Multi-Path Cross-Modal Traction for Compositional Zero-Shot Learning (CVPR 2024 · similarity 0.91)
- Retrieval-Augmented Primitive Representations for Compositional Zero-Shot Learning (AAAI 2024 · similarity 0.91)
- Context-based and Diversity-driven Specificity in Compositional Zero-Shot Learning (CVPR 2024 · similarity 0.90)
- ProCC: Progressive Cross-Primitive Compatibility for Open-World Compositional Zero-Shot Learning (AAAI 2024 · similarity 0.90)
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.
