Disentangling Before Composing : Learning Invariant Disentangled Features for Compositional Zero-Shot Learning

Compositional Zero-Shot Learning (CZSL) aims to recognize novel compositions using knowledge learned from seen attribute-object compositions in the training set. Previous works mainly project an image and its corresponding composition into a common embedding space to measure their compatibility scor...

Ausführliche Beschreibung

Bibliographische Detailangaben

Veröffentlicht in:	IEEE transactions on pattern analysis and machine intelligence. - 1979. - PP(2024) vom: 28. Okt.
1. Verfasser:	Zhang, Tian (VerfasserIn)
Weitere Verfasser:	Liang, Kongming, Du, Ruoyi, Chen, Wei, Ma, Zhanyu
Format:	Online-Aufsatz
Sprache:	English
Veröffentlicht:	2024
Zugriff auf das übergeordnete Werk:	IEEE transactions on pattern analysis and machine intelligence
Schlagworte:	Journal Article