Simple Primitives With Feasibility- and Contextuality-Dependence for Open-World Compositional Zero-Shot Learning

Abstract

This paper proposes the SAD-SP model, which improves open-world compositional zero-shot learning by capturing contextuality and feasibility dependencies between states and objects. Using semantic attention and knowledge disentanglement, the approach enhances performance on benchmarks like MIT-States and C-GQA by predicting unseen compositions more accurately.

Publication
IEEE Transactions on Pattern Analysis and Machine Intelligence