AI Paper Atlas

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

TPAMI 2023 · Label-efficient and robust learning › Zero-/few-shot and meta-learning · approach: Generative feature synthesis for zero-shot · 26 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 knowledge disentanglement (KD) to SP (ablation)SP · UT-ZapposHM: 43.441 -> 44.068Improved
add knowledge disentanglement (KD) to SP (ablation)SP · C-GQAHM: 5.795 -> 6.086Improved
add semantic attention (SA) to SP (ablation)SP · UT-ZapposAUC: 28.425 -> 28.166Hurt
add semantic attention (SA) to SP (ablation)SP · C-GQAAUC: 0.964 -> 0.975Improved
add both SA and KD to SP (ablation)SP · MIT-StatesAUC: 1.270 -> 1.362Improved
add state contextuality branch p_c(s) (ablation)SAD-SP · UT-ZapposAUC: 26.287 -> 28.406Improved
add state contextuality branch p_c(s) (ablation)SAD-SP · C-GQAAUC: 1.045 -> 1.002Hurt
add object feasibility branch p_f(o|s) (ablation)SAD-SP · MIT-StatesAUC: 1.272 -> 1.362Improved
add object feasibility branch p_f(o|s) (ablation)SAD-SP_ff · C-GQAAUC: 0.877 -> 0.856Hurt
end-to-end backbone fine-tuning instead of fixed backbone (ablation)SAD-SP · UT-ZapposAUC: 23.1 -> 28.4Improved
SAD-SP (feasibility and contextuality) versus KG-SP with external knowledgeKG-SP · C-GQAAUC: 0.78 -> 1.002Improved
SAD-SP versus KG-SPKG-SP · MIT-StatesHM: 7.4 -> 7.8Improved

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.

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

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