AI Paper Atlas

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

ICCV 2025 · Label-efficient and robust learning › Zero-/few-shot and meta-learning · approach: Generative feature synthesis for zero-shot · 2 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
add text-enhanced object learning (TEO) (ablation)CPF · C-GQA closed-worldAUC: 7.6 -> 8.2Improved
add object-guided attribute learning (OGA) on top of TEO (ablation)CPF · C-GQA closed-worldAUC: 6.9 -> 7.6Improved
add TEO (ablation)CPF · C-GQA open-worldAUC: 1.79 -> 2.10Improved
add OGA on top of TEO (ablation)CPF · C-GQA open-worldAUC: 1.69 -> 1.79Improved
add TEO (ablation)CPF · C-GQA closed-worldSeen accuracy: 39.6 -> 39.6No clear effect
use cross-attention instead of averaging for attribute guidance (Eq. 2) (ablation)CPF · C-GQA closed-worldAUC: 7.8 -> 8.2Improved
use cross-attention instead of averaging (Eq. 4) (ablation)CPF · C-GQA closed-worldAUC: 7.1 -> 8.2Improved
use cross-attention instead of averaging (Eq. 2) (ablation)CPF · C-GQA open-worldAUC: 1.91 -> 2.10Improved
add shallow-level features to deep-level visual embeddings (ablation)CPF · C-GQA closed-worldAUC: 6.7 -> 8.2Improved
add shallow-level features to deep-level visual embeddings (ablation)CPF · C-GQA open-worldAUC: 1.58 -> 2.10Improved
condition on object visual embedding instead of attribute text embedding for attribute guidance (ablation)CPF · C-GQA closed-worldAUC: 7.6 -> 8.2Improved
condition on object visual embedding instead of object text embedding (ablation)CPF · C-GQA closed-worldAUC: 7.7 -> 8.2Improved

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