Mutual Balancing in State-Object Components for Compositional Zero-Shot Learning

Chenyi Jiang, Qiaolin Ye, Shidong Wang, Yuming Shen, Zheng Zhang, Haofeng Zhang

Abstract: Highlights•The method considers CZSL as an unbalanced multi-label classification, utilizing visual deviation of components to provide an inductive bias.•Component imbalance info is used to re-weight CZSL training, enabling the model to reconstruct inter-component balance.•The method outperforms SoTAs with base CZSL methods, and augments joint embedding function based approaches.