Cross-composition Feature Disentanglement for Compositional Zero-shot Learning
Disentanglement of visual features of primitives (i.e., attributes and objects) has shown exceptional results in Compositional Zero-shot Learning (CZSL). However, due to the feature divergence of an attribute (resp. object) when combined with different objects (resp. attributes), it is challenging to learn disentangled primitive features that are general across different compositions. To this end, we propose the solution of cross-composition feature disentanglement, which takes multiple primitive-sharing compositions as inputs and constrains the disentangled primitive features to be general across these compositions. More specifically, we leverage a compositional graph to define the overall primitive-sharing relationships between compositions, and build a task-specific architecture upon the recently successful large pre-trained vision-language model (VLM) CLIP, with dual cross-composition disentangling adapters (called L-Adapter and V-Adapter) inserted into CLIP's frozen text and image encoders, respectively. Evaluation on three popular CZSL benchmarks shows that our proposed solution significantly improves the performance of CZSL, and its components have been verified by solid ablation studies.
Code (0)
등록된 구현이 없습니다.
Tasks
AttributeCompositional Zero-Shot LearningDisentanglementLanguage ModelingLanguage ModellingZero-Shot LearningMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Compositional Zero-Shot Learning: A Survey
Compositional Zero-Shot Learning (CZSL) is a critical task in computer vision that enables models to recognize unseen combinations of known attributes and objects during inference, addressing the combinatorial challenge …
Compositional Zero-Shot LearningCAMS: Towards Compositional Zero-Shot Learning via Gated Cross-Attention and Multi-Space Disentanglement
Compositional zero-shot learning (CZSL) aims to learn the concepts of attributes and objects in seen compositions and to recognize their unseen compositions. Most Contrastive Language-Image Pre-training (CLIP)-based CZSL…
Compositional Zero-Shot LearningLearning Attention as Disentangler for Compositional Zero-shot Learning
Compositional zero-shot learning (CZSL) aims at learning visual concepts (i.e., attributes and objects) from seen compositions and combining concept knowledge into unseen compositions. The key to CZSL is learning the dis…
AttributeCompositional Zero-Shot LearningDisentanglementZero-Shot LearningRecursive Disentanglement Network
Disentangled feature representation is essential for data-efficient learning. The feature space of deep models is inherently compositional. Existing $\beta$-VAE-based methods, which only apply disentanglement regularizat…
DisentanglementInductive BiasRepresentation LearningVisual Referential Games Further the Emergence of Disentangled Representations
Natural languages are powerful tools wielded by human beings to communicate information. Among their desirable properties, compositionality has been the main focus in the context of referential games and variants, as it …
DisentanglementInformativeness