mlsanityData to 7 Oct 2026

Graph-guided Cross-composition Feature Disentanglement for Compositional Zero-shot Learning

arXiv 2408.09786 ↗First posted 19 Aug 2024cs.CVcited by 0

Not on the map. Why?

Abstract (arXiv)

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. Our code and data are available at:https://github.com/zhurunkai/DCDA.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 10 of its 27 references that are in the map. First posted on arXiv 19 Aug 2024.

Builds on

10 of 27 references.

References · 10

  1. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,456
  2. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 29,915
  3. 2021KnowPrompt: Knowledge-aware Prompt-tuning with Synergistic Optimization for Relation Extractioncited by 180
  4. 2019Task-Driven Modular Networks for Zero-Shot Compositional Learningcited by 121
  5. 2021Learning Graph Embeddings for Compositional Zero-shot Learningcited by 112
  6. 2021Open World Compositional Zero-Shot Learningcited by 100
  7. 2020Symmetry and Group in Attribute-Object Compositionscited by 89
  8. 2022Disentangling Visual Embeddings for Attributes and Objectscited by 55
  9. 2021OntoZSL: Ontology-enhanced Zero-shot Learningcited by 45
  10. 2021Zero-shot and Few-shot Learning with Knowledge Graphs: A Comprehensive Surveycited by 23

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2026FlowComposer: Composable Flows for Compositional Zero-Shot Learning
  2. 2025Learning Visual Proxy for Compositional Zero-Shot Learning
  3. 2023CAILA: Concept-Aware Intra-Layer Adapters for Compositional Zero-Shot Learning
  4. 2026DIFFCZSL: Compositional Zero-Shot Learning Regularized by Diffusion Representations
  5. 2024Leveraging MLLM Embeddings and Attribute Smoothing for Compositional Zero-Shot Learning
  6. 2023Prompting Language-Informed Distribution for Compositional Zero-Shot Learning
  7. 2025Semantically Guided Dynamic Visual Prototype Refinement for Compositional Zero-Shot Learning
  8. 2024Unified Framework for Open-World Compositional Zero-shot Learning