Research map / Label-efficient and robust learning / Zero-/few-shot and meta-learning
Simple Primitives With Feasibility- and Contextuality-Dependence for Open-World Compositional Zero-Shot Learning
Zhe Liu, Yun Li, Lina Yao, Xiaojun Chang, Wei Fang, Xiao‐Jun Wu, Abdulmotaleb El Saddik
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 knowledge disentanglement (KD) to SP (ablation) | SP · UT-Zappos | HM: 43.441 -> 44.068 | Improved |
| add knowledge disentanglement (KD) to SP (ablation) | SP · C-GQA | HM: 5.795 -> 6.086 | Improved |
| add semantic attention (SA) to SP (ablation) | SP · UT-Zappos | AUC: 28.425 -> 28.166 | Hurt |
| add semantic attention (SA) to SP (ablation) | SP · C-GQA | AUC: 0.964 -> 0.975 | Improved |
| add both SA and KD to SP (ablation) | SP · MIT-States | AUC: 1.270 -> 1.362 | Improved |
| add state contextuality branch p_c(s) (ablation) | SAD-SP · UT-Zappos | AUC: 26.287 -> 28.406 | Improved |
| add state contextuality branch p_c(s) (ablation) | SAD-SP · C-GQA | AUC: 1.045 -> 1.002 | Hurt |
| add object feasibility branch p_f(o|s) (ablation) | SAD-SP · MIT-States | AUC: 1.272 -> 1.362 | Improved |
| add object feasibility branch p_f(o|s) (ablation) | SAD-SP_ff · C-GQA | AUC: 0.877 -> 0.856 | Hurt |
| end-to-end backbone fine-tuning instead of fixed backbone (ablation) | SAD-SP · UT-Zappos | AUC: 23.1 -> 28.4 | Improved |
| SAD-SP (feasibility and contextuality) versus KG-SP with external knowledge | KG-SP · C-GQA | AUC: 0.78 -> 1.002 | Improved |
| SAD-SP versus KG-SP | KG-SP · MIT-States | HM: 7.4 -> 7.8 | Improved |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.
- KG-SP — KG-SP: Knowledge Guided Simple Primitives for Open World Compositional Zero-Shot Learning (CVPR 2022) · better on 6 of 6 shared results
Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.
Closest papers by meaning
- ProCC: Progressive Cross-Primitive Compatibility for Open-World Compositional Zero-Shot Learning (AAAI 2024 · similarity 0.92)
- Beyond Seen Primitive Concepts and Attribute-Object Compositional Learning (CVPR 2024 · similarity 0.92)
- Context-based and Diversity-driven Specificity in Compositional Zero-Shot Learning (CVPR 2024 · similarity 0.91)
- A Dynamic Learning Method towards Realistic Compositional Zero-Shot Learning (AAAI 2024 · similarity 0.91)
- Troika: Multi-Path Cross-Modal Traction for Compositional Zero-Shot Learning (CVPR 2024 · similarity 0.90)
- LOGICZSL: Exploring Logic-induced Representation for Compositional Zero-shot Learning (CVPR 2025 · similarity 0.90)
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.
