Learning Primitive Relations for Compositional Zero-Shot Learning

Insu Lee; Jiseob Kim; Kyuhong Shim; Byonghyo Shim

ICASSP 2025accepted0 citations

Learning Primitive Relations for Compositional Zero-Shot Learning

Insu Lee, Jiseob Kim, Kyuhong Shim, Byonghyo Shim

Abstract

Compositional Zero-Shot Learning (CZSL) aims to identify unseen state-object compositions by leveraging knowledge learned from seen compositions. Existing approaches often independently predict states and objects, overlooking their relationships. In this paper, we propose a novel framework, learning primitive relations (LPR), designed to probabilistically capture the relationships between states and objects. By employing the cross-attention mechanism, LPR considers the dependencies between states and objects, enabling the model to infer the likelihood of unseen compositions. Experimental results demonstrate that LPR outperforms state-of-the-art methods on all three CZSL benchmark datasets in both closed-world and open-world settings. Through qualitative analysis, we show that LPR leverages state-object relationships for unseen composition prediction.

BibTeX

@inproceedings{icassp2025_learningprimitiv,
  title = {Learning Primitive Relations for Compositional Zero-Shot Learning},
  author = {Insu Lee and Jiseob Kim and Kyuhong Shim and Byonghyo Shim},
  booktitle = {ICASSP 2025},
  year = {2025}
}