CSCNET: Class-Specified Cascaded Network for Compositional Zero-Shot Learning
This work addresses a fundamental challenge in recognizing novel attribute-object compositions for zero-shot learning, though it appears incremental as it builds on existing disentanglement methods.
The paper tackles the problem of attribute-object disentanglement in compositional zero-shot learning by proposing CSCNet, a cascaded network that classifies one primitive and uses it to guide the other, achieving superior results compared to previous methods.
Attribute and object (A-O) disentanglement is a fundamental and critical problem for Compositional Zero-shot Learning (CZSL), whose aim is to recognize novel A-O compositions based on foregone knowledge. Existing methods based on disentangled representation learning lose sight of the contextual dependency between the A-O primitive pairs. Inspired by this, we propose a novel A-O disentangled framework for CZSL, namely Class-specified Cascaded Network (CSCNet). The key insight is to firstly classify one primitive and then specifies the predicted class as a priori for guiding another primitive recognition in a cascaded fashion. To this end, CSCNet constructs Attribute-to-Object and Object-to-Attribute cascaded branches, in addition to a composition branch modeling the two primitives as a whole. Notably, we devise a parametric classifier (ParamCls) to improve the matching between visual and semantic embeddings. By improving the A-O disentanglement, our framework achieves superior results than previous competitive methods.