mlsanityData to 7 Oct 2026

Context-based and Diversity-driven Specificity in Compositional Zero-Shot Learning

arXiv 2402.17251 ↗First posted 27 Feb 2024cs.CVcited by 20

Not on the map. Why?

Abstract (arXiv)

Compositional Zero-Shot Learning (CZSL) aims to recognize unseen attribute-object pairs based on a limited set of observed examples. Current CZSL methodologies, despite their advancements, tend to neglect the distinct specificity levels present in attributes. For instance, given images of sliced strawberries, they may fail to prioritize `Sliced-Strawberry' over a generic `Red-Strawberry', despite the former being more informative. They also suffer from ballooning search space when shifting from Close-World (CW) to Open-World (OW) CZSL. To address the issues, we introduce the Context-based and Diversity-driven Specificity learning framework for CZSL (CDS-CZSL). Our framework evaluates the specificity of attributes by considering the diversity of objects they apply to and their related context. This novel approach allows for more accurate predictions by emphasizing specific attribute-object pairs and improves composition filtering in OW-CZSL. We conduct experiments in both CW and OW scenarios, and our model achieves state-of-the-art results across three datasets.

Key facts. Cited by 20 papers in the map (data through 7 Oct 2026). Builds on 30 of its 44 references that are in the map. First posted on arXiv 27 Feb 2024.

Builds on

30 of 44 references.

References · 30

  1. 2017Attention Is All You Needcited by 59,932
  2. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,456
  3. 2020Language Models are Few-Shot Learnerscited by 32,199
  4. 2021Prefix-Tuning: Optimizing Continuous Prompts for Generationcited by 3,878
  5. 2021Learning to Prompt for Vision-Language Modelscited by 2,269
  6. 2017Learning multiple visual domains with residual adapterscited by 553
  7. 2021Parameter-efficient Multi-task Fine-tuning for Transformers via Shared Hypernetworkscited by 278
  8. 2021PPT: Pre-trained Prompt Tuning for Few-shot Learningcited by 232
  9. 2018Efficient parametrization of multi-domain deep neural networkscited by 168
  10. 2019Task-Driven Modular Networks for Zero-Shot Compositional Learningcited by 121
  11. 2021Learning Graph Embeddings for Compositional Zero-shot Learningcited by 112
  12. 2021Open World Compositional Zero-Shot Learningcited by 100
18 more
  1. 2020Symmetry and Group in Attribute-Object Compositionscited by 89
  2. 2021Detecting Human-Object Interaction via Fabricated Compositional Learningcited by 79
  3. 2022Learning to Compose Soft Prompts for Compositional Zero-Shot Learningcited by 66
  4. 2022Disentangling Visual Embeddings for Attributes and Objectscited by 55
  5. 2022Siamese Contrastive Embedding Network for Compositional Zero-Shot Learningcited by 55
  6. 2023CLIP-Guided Vision-Language Pre-training for Question Answering in 3D Scenescited by 55
  7. 2021Learning Graph Embeddings for Open World Compositional Zero-Shot Learningcited by 49
  8. 2022KG-SP: Knowledge Guided Simple Primitives for Open World Compositional Zero-Shot Learningcited by 41
  9. 2023Learning Attention as Disentangler for Compositional Zero-shot Learningcited by 29
  10. 2023Learning Conditional Attributes for Compositional Zero-Shot Learningcited by 28
  11. 2021Relation-aware Compositional Zero-shot Learning for Attribute-Object Pair Recognitioncited by 19
  12. 2021Zero-Shot Compositional Concept Learningcited by 16
  13. 20213D Compositional Zero-shot Learning with DeCompositional Consensuscited by 16
  14. 2023Hierarchical Visual Primitive Experts for Compositional Zero-Shot Learningcited by 16
  15. 2022On Leveraging Variational Graph Embeddings for Open World Compositional Zero-Shot Learningcited by 13
  16. 2023Distilled Reverse Attention Network for Open-world Compositional Zero-Shot Learningcited by 11
  17. 2022Distinctive Image Captioning via CLIP Guided Group Optimizationcited by 6
  18. 2021Rethink, Revisit, Revise: A Spiral Reinforced Self-Revised Network for Zero-Shot Learningcited by 5

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 3; 2025: 13; 2026: 4.

20 papers.

Sort:

By area:

  1. 2025Learning Clustering-based Prototypes for Compositional Zero-shot Learningcited by 13
  2. 2025Generate, Refine, and Encode: Leveraging Synthesized Novel Samples for On-the-Fly Fine-Grained Category Discoverycited by 9
  3. 2024TsCA: On the Semantic Consistency Alignment via Conditional Transport for Compositional Zero-Shot Learningcited by 6
  4. 2024On the Element-Wise Representation and Reasoning in Zero-Shot Image Recognition: A Systematic Surveycited by 5
  5. 2026FlowComposer: Composable Flows for Compositional Zero-Shot Learningcited by 3
  6. 2024Not Just Object, But State: Compositional Incremental Learning without Forgettingcited by 2
  7. 2025Learning Visual Proxy for Compositional Zero-Shot Learningcited by 2
  8. 2025Visual Adaptive Prompting for Compositional Zero-Shot Learningcited by 2
  9. 2025A Conditional Probability Framework for Compositional Zero-shot Learningcited by 2
  10. 2025Learning Primitive Relations for Compositional Zero-Shot Learningcited by 1
  11. 2025MSCI: Addressing CLIP's Inherent Limitations for Compositional Zero-Shot Learningcited by 1
  12. 2025CAMS: Towards Compositional Zero-Shot Learning via Gated Cross-Attention and Multi-Space Disentanglementcited by 1
8 more
  1. 2025H2em: Learning Hierarchical Hyperbolic Embeddings for Compositional Zero-Shot Learningcited by 1
  2. 2025Semantically Guided Dynamic Visual Prototype Refinement for Compositional Zero-Shot Learningcited by 0
  3. 2025Multi-Sourced Compositional Generalization in Visual Question Answeringcited by 0
  4. 2025EVA: Mixture-of-Experts Semantic Variant Alignment for Compositional Zero-Shot Learningcited by 0
  5. 2025Prompt-Based Continual Compositional Zero-Shot Learningcited by 0
  6. 2026Why Can't I Open My Drawer? Mitigating Object-Driven Shortcuts in Zero-Shot Compositional Action Recognitioncited by 0
  7. 2026DIFFCZSL: Compositional Zero-Shot Learning Regularized by Diffusion Representationscited by 0
  8. 2026From Model Patterns to Abstract Semantics in Compositional Zero-Shot Learningcited by 0