Research map / Vision-language and multimodal / CLIP and zero-shot
Understanding Multi-compositional learning in Vision and Language models via Category Theory
Sotirios Panagiotis Chytas, Hyunwoo J Kim, Vikas Singh
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 |
|---|---|---|---|
| treat attributes as morphisms (CatCom) rather than as objects in a product category | SymNet-style / CGE-style CZSL · C-GQA closed-world | AUC: 3.6 -> 4.3 (CGE_t vs CatCom_t) | Improved |
| train the backbone (CatCom_t) instead of frozen backbone (ablation) | CatCom · UT-Zappos closed-world | AUC: 29.2 -> 35.3 | Improved |
| train the backbone (CatCom_t) instead of frozen backbone (ablation) | CatCom · MIT-States closed-world | AUC: 5.7 -> 6.3 | Improved |
| use CatCom_t versus CGE_t on MIT-States closed world | CatCom_t · MIT-States closed-world | AUC: 6.5 -> 6.3 | Hurt |
| apply CatCom to multi-attribute composition without adjustment | CatCom · aPY | mAUC: 83.4 -> 84.7 (SymNet_m vs CatCom) | Improved |
| apply CatCom to SUN multi-attribute composition | CatCom · SUN | mAUC: 88.4 -> 87.9 | Hurt |
Closest papers by meaning
- Beyond Seen Primitive Concepts and Attribute-Object Compositional Learning (CVPR 2024 · similarity 0.91)
- Iterated Learning Improves Compositionality in Large Vision-Language Models (CVPR 2024 · similarity 0.90)
- Troika: Multi-Path Cross-Modal Traction for Compositional Zero-Shot Learning (CVPR 2024 · similarity 0.89)
- Revealing the Proximate Long-Tail Distribution in Compositional Zero-Shot Learning (AAAI 2024 · similarity 0.89)
- Not Only Text: Exploring Compositionality of Visual Representations in Vision-Language Models (CVPR 2025 · similarity 0.89)
- LOGICZSL: Exploring Logic-induced Representation for Compositional Zero-shot Learning (CVPR 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.
