mlsanityData to 14 Oct 2026

Open World Compositional Zero-Shot Learning

arXiv 2101.12609 ↗First posted 29 Jan 2021cs.CV cs.LGcited by 101

Not on the map. Why?

Abstract (arXiv)

Compositional Zero-Shot learning (CZSL) requires to recognize state-object compositions unseen during training. In this work, instead of assuming prior knowledge about the unseen compositions, we operate in the open world setting, where the search space includes a large number of unseen compositions some of which might be unfeasible. In this setting, we start from the cosine similarity between visual features and compositional embeddings. After estimating the feasibility score of each composition, we use these scores to either directly mask the output space or as a margin for the cosine similarity between visual features and compositional embeddings during training. Our experiments on two standard CZSL benchmarks show that all the methods suffer severe performance degradation when applied in the open world setting. While our simple CZSL model achieves state-of-the-art performances in the closed world scenario, our feasibility scores boost the performance of our approach in the open world setting, clearly outperforming the previous state of the art.

Key facts. Cited by 101 papers in the map (data through 14 Oct 2026). Builds on 19 of its 38 references that are in the map. First posted on arXiv 29 Jan 2021.

Builds on

19 of 38 references.

References · 19

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2014Adam: A Method for Stochastic Optimizationcited by 37,240
  3. 2016Layer Normalizationcited by 5,669
  4. 2013Distributed Representations of Words and Phrases and their Compositionalitycited by 3,474
  5. 2016Enriching Word Vectors with Subword Informationcited by 1,583
  6. 2016CLEVR: A Diagnostic Dataset for Compositional Language and Elementary Visual Reasoningcited by 1,457
  7. 2017Zero-Shot Learning -- A Comprehensive Evaluation of the Good, the Bad and the Uglycited by 538
  8. 2018Dynamic Few-Shot Visual Learning without Forgettingcited by 385
  9. 2014Towards Open World Recognitioncited by 226
  10. 2018Compositional Attention Networks for Machine Reasoningcited by 183
  11. 2019Task-Driven Modular Networks for Zero-Shot Compositional Learningcited by 121
  12. 2020Symmetry and Group in Attribute-Object Compositionscited by 89
7 more
  1. 2019AdaCos: Adaptively Scaling Cosine Logits for Effectively Learning Deep Face Representationscited by 83
  2. 2016Semantic Jitter: Dense Supervision for Visual Comparisons via Synthetic Imagescited by 45
  3. 2019Language Models with Transformerscited by 36
  4. 2019How to make a pizza: Learning a compositional layer-based GAN modelcited by 21
  5. 2018Attributes as Operators: Factorizing Unseen Attribute-Object Compositionscited by 20
  6. 2018Modular Generative Adversarial Networkscited by 16
  7. 2016Semi-supervised Vocabulary-informed Learningcited by 8

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 7; 2022: 25; 2023: 25; 2024: 21; 2025: 17; 2026: 6.

101 papers.

Sort:

By area:

  1. 2023WinCLIP: Zero-/Few-Shot Anomaly Classification and Segmentationcited by 315
  2. 2022Language in a Bottle: Language Model Guided Concept Bottlenecks for Interpretable Image Classificationcited by 312
  3. 2023Linguistic Binding in Diffusion Models: Enhancing Attribute Correspondence through Attention Map Alignmentcited by 171
  4. 2023Vision-by-Language for Training-Free Compositional Image Retrievalcited by 103
  5. 2022Does CLIP Bind Concepts? Probing Compositionality in Large Image Modelscited by 102
  6. 2021Everything at Once -- Multi-modal Fusion Transformer for Video Retrievalcited by 79
  7. 2022Learning to Compose Soft Prompts for Compositional Zero-Shot Learningcited by 67
  8. 2022Compositional Temporal Grounding with Structured Variational Cross-Graph Correspondence Learningcited by 59
  9. 2022Siamese Contrastive Embedding Network for Compositional Zero-Shot Learningcited by 55
  10. 2022I2MVFormer: Large Language Model Generated Multi-View Document Supervision for Zero-Shot Image Classificationcited by 54
  11. 2021Learning Graph Embeddings for Open World Compositional Zero-Shot Learningcited by 49
  12. 2022KG-SP: Knowledge Guided Simple Primitives for Open World Compositional Zero-Shot Learningcited by 41
38 more
  1. 2022Disentanglement of Correlated Factors via Hausdorff Factorized Supportcited by 37
  2. 2022Decomposed Soft Prompt Guided Fusion Enhancing for Compositional Zero-Shot Learningcited by 37
  3. 2023Learning Object State Changes in Videos: An Open-World Perspectivecited by 36
  4. 2022Do Vision-Language Pretrained Models Learn Composable Primitive Concepts?cited by 31
  5. 2022Revisiting Open World Object Detectioncited by 30
  6. 2022BatchFormer: Learning to Explore Sample Relationships for Robust Representation Learningcited by 29
  7. 2022Probabilistic Compositional Embeddings for Multimodal Image Retrievalcited by 29
  8. 2023Learning Attention as Disentangler for Compositional Zero-shot Learningcited by 29
  9. 2023Learning Conditional Attributes for Compositional Zero-Shot Learningcited by 28
  10. 2022I2DFormer: Learning Image to Document Attention for Zero-Shot Image Classificationcited by 27
  11. 2023Troika: Multi-Path Cross-Modal Traction for Compositional Zero-Shot Learningcited by 27
  12. 2022Learning Invariant Visual Representations for Compositional Zero-Shot Learningcited by 24
  13. 2023Prompting Language-Informed Distribution for Compositional Zero-Shot Learningcited by 24
  14. 2022Learning Attention Propagation for Compositional Zero-Shot Learningcited by 20
  15. 2024Context-based and Diversity-driven Specificity in Compositional Zero-Shot Learningcited by 20
  16. 2023DRPT: Disentangled and Recurrent Prompt Tuning for Compositional Zero-Shot Learningcited by 17
  17. 20213D Compositional Zero-shot Learning with DeCompositional Consensuscited by 16
  18. 2023Hierarchical Visual Primitive Experts for Compositional Zero-Shot Learningcited by 16
  19. 2023GIPCOL: Graph-Injected Soft Prompting for Compositional Zero-Shot Learningcited by 16
  20. 2024AAPL: Adding Attributes to Prompt Learning for Vision-Language Modelscited by 14
  21. 2025Learning Clustering-based Prototypes for Compositional Zero-shot Learningcited by 14
  22. 2022On Leveraging Variational Graph Embeddings for Open World Compositional Zero-Shot Learningcited by 13
  23. 2023Preserving Modality Structure Improves Multi-Modal Learningcited by 13
  24. 2023Chop & Learn: Recognizing and Generating Object-State Compositionscited by 13
  25. 2022Prompting Large Pre-trained Vision-Language Models For Compositional Concept Learningcited by 12
  26. 2023Compositional Zero-shot Learning via Progressive Language-based Observationscited by 12
  27. 2023Distilled Reverse Attention Network for Open-world Compositional Zero-Shot Learningcited by 11
  28. 2023Learning Adversarial Semantic Embeddings for Zero-Shot Recognition in Open Worldscited by 11
  29. 2025Training-Free Personalization via Retrieval and Reasoning on Fingerprintscited by 10
  30. 2022ProCC: Progressive Cross-primitive Compatibility for Open-World Compositional Zero-Shot Learningcited by 9
  31. 2024C2C: Component-to-Composition Learning for Zero-Shot Compositional Action Recognitioncited by 9
  32. 2024CusConcept: Customized Visual Concept Decomposition with Diffusion Modelscited by 9
  33. 2021Zero-Shot Action Recognition from Diverse Object-Scene Compositionscited by 8
  34. 2023Revealing the Proximate Long-Tail Distribution in Compositional Zero-Shot Learningcited by 8
  35. 2022Overcoming Shortcut Learning in a Target Domain by Generalizing Basic Visual Factors from a Source Domaincited by 7
  36. 2023CAILA: Concept-Aware Intra-Layer Adapters for Compositional Zero-Shot Learningcited by 7
  37. 2024TsCA: On the Semantic Consistency Alignment via Conditional Transport for Compositional Zero-Shot Learningcited by 6
  38. 2024Multimodal Emotion Recognition using Audio-Video Transformer Fusion with Cross Attentioncited by 5

50 most cited of 101 All 101 (JSON)