AI Paper Atlas

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

ECCV 2024 · Vision-language and multimodal › CLIP and zero-shot · approach: Attribute-based zero-shot learning · 6 citations (OpenAlex)

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 changedWhereMeasuredEffect
treat attributes as morphisms (CatCom) rather than as objects in a product categorySymNet-style / CGE-style CZSL · C-GQA closed-worldAUC: 3.6 -> 4.3 (CGE_t vs CatCom_t)Improved
train the backbone (CatCom_t) instead of frozen backbone (ablation)CatCom · UT-Zappos closed-worldAUC: 29.2 -> 35.3Improved
train the backbone (CatCom_t) instead of frozen backbone (ablation)CatCom · MIT-States closed-worldAUC: 5.7 -> 6.3Improved
use CatCom_t versus CGE_t on MIT-States closed worldCatCom_t · MIT-States closed-worldAUC: 6.5 -> 6.3Hurt
apply CatCom to multi-attribute composition without adjustmentCatCom · aPYmAUC: 83.4 -> 84.7 (SymNet_m vs CatCom)Improved
apply CatCom to SUN multi-attribute compositionCatCom · SUNmAUC: 88.4 -> 87.9Hurt

Closest papers by meaning

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.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy