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
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 causal intervention (disentangle-compose-disentangle) loss (ablation) | I2CD · C-GQA closed-world | AUC: 15.7 -> 16.3 | Improved |
| add causal intervention loss (ablation) | I2CD · MIT-States closed-world | AUC: 22.6 -> 23.3 | Improved |
| add causal intervention loss (ablation) | I2CD · UT-Zappos open-world | AUC: 34.6 -> 35.6 | Improved |
| add invertible disentanglement losses (ablation) | I2CD · UT-Zappos closed-world | AUC: 43.2 -> 46.4 | Improved |
| add invertible disentanglement losses (ablation) | I2CD · C-GQA open-world | AUC: 3.58 -> 4.18 | Improved |
| I2CD vs CAILA | I2CD · MIT-States closed-world | AUC: 23.4 -> 23.3 | No clear effect |
| I2CD vs CAILA/Troika | I2CD · UT-Zappos closed-world | AUC: 44.1 -> 46.4 | Improved |
| I2CD vs CDS-CZSL | I2CD · MIT-States open-world | AUC: 8.5 -> 8.2 | Hurt |
| I2CD vs CAILA | I2CD · C-GQA open-world | AUC: 3.08 -> 4.25 | Mixed |
Closest papers by meaning
- A Dynamic Learning Method towards Realistic Compositional Zero-Shot Learning (AAAI 2024 · similarity 0.88)
- Beyond Seen Primitive Concepts and Attribute-Object Compositional Learning (CVPR 2024 · similarity 0.88)
- Disentangled Representation Learning via Modular Compositional Bias (NeurIPS 2025 · similarity 0.87)
- Revealing the Proximate Long-Tail Distribution in Compositional Zero-Shot Learning (AAAI 2024 · similarity 0.87)
- Fully Distributed, Flexible Compositional Visual Representations via Soft Tensor Products (NeurIPS 2024 · similarity 0.87)
- LOGICZSL: Exploring Logic-induced Representation for Compositional Zero-shot Learning (CVPR 2025 · similarity 0.87)
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.
