AI Paper Atlas

Research map / Label-efficient and robust learning / Zero-/few-shot and meta-learning

I2CD: An Invertible Causal Framework for Compositional Zero-Shot Learning via Disentangle-Compose-Disentangle

Zhaoquan Yuan, Zining Wang, Yuankang Pan, Ao Luo, Wei Li, Xiao Wu, Changsheng Xu

AAAI 2026 · Label-efficient and robust learning › Zero-/few-shot and meta-learning · approach: Generative feature synthesis for zero-shot · 0 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 causal intervention (disentangle-compose-disentangle) loss (ablation)I2CD · C-GQA closed-worldAUC: 15.7 -> 16.3Improved
add causal intervention loss (ablation)I2CD · MIT-States closed-worldAUC: 22.6 -> 23.3Improved
add causal intervention loss (ablation)I2CD · UT-Zappos open-worldAUC: 34.6 -> 35.6Improved
add invertible disentanglement losses (ablation)I2CD · UT-Zappos closed-worldAUC: 43.2 -> 46.4Improved
add invertible disentanglement losses (ablation)I2CD · C-GQA open-worldAUC: 3.58 -> 4.18Improved
I2CD vs CAILAI2CD · MIT-States closed-worldAUC: 23.4 -> 23.3No clear effect
I2CD vs CAILA/TroikaI2CD · UT-Zappos closed-worldAUC: 44.1 -> 46.4Improved
I2CD vs CDS-CZSLI2CD · MIT-States open-worldAUC: 8.5 -> 8.2Hurt
I2CD vs CAILAI2CD · C-GQA open-worldAUC: 3.08 -> 4.25Mixed

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