CSCNET: Class-Specified Cascaded Network for Compositional Zero-Shot Learning
Not on the map. Why?
Abstract (arXiv)
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.
Key facts. Cited by 1 paper in the map (data through 7 Oct 2026). Builds on 16 of its 26 references that are in the map. First posted on arXiv 9 Mar 2024.
Builds on
16 of 26 references.
References · 16
- 2015Deep Residual Learning for Image Recognitioncited by 51,809
- 2014Adam: A Method for Stochastic Optimizationcited by 36,960
- 2013Efficient Estimation of Word Representations in Vector Spacecited by 4,346
- 2016Enriching Word Vectors with Subword Informationcited by 1,578
- 2019Task-Driven Modular Networks for Zero-Shot Compositional Learningcited by 121
- 2021Open World Compositional Zero-Shot Learningcited by 100
- 2020Symmetry and Group in Attribute-Object Compositionscited by 89
- 2020A causal view of compositional zero-shot recognitioncited by 78
- 2021Lifelong Person Re-Identification via Adaptive Knowledge Accumulationcited by 57
- 2022Disentangling Visual Embeddings for Attributes and Objectscited by 55
- 2022Siamese Contrastive Embedding Network for Compositional Zero-Shot Learningcited by 55
- 2023Learning Attention as Disentangler for Compositional Zero-shot Learningcited by 29
4 more
- 2023Learning Conditional Attributes for Compositional Zero-Shot Learningcited by 28
- 2022Learning Invariant Visual Representations for Compositional Zero-Shot Learningcited by 24
- 2020Dual Gaussian-based Variational Subspace Disentanglement for Visible-Infrared Person Re-Identificationcited by 23
- 2021Relation-aware Compositional Zero-shot Learning for Attribute-Object Pair Recognitioncited by 19
Built on by
Citing papers per year: 2024: 1.
1 paper.