mlsanityData to 7 Oct 2026

An Empirical Study and Analysis of Generalized Zero-Shot Learning for Object Recognition in the Wild

arXiv 1605.04253 ↗First posted 13 May 2016cs.CVcited by 146

Not on the map. Why?

Abstract (arXiv)

Zero-shot learning (ZSL) methods have been studied in the unrealistic setting where test data are assumed to come from unseen classes only. In this paper, we advocate studying the problem of generalized zero-shot learning (GZSL) where the test data's class memberships are unconstrained. We show empirically that naively using the classifiers constructed by ZSL approaches does not perform well in the generalized setting. Motivated by this, we propose a simple but effective calibration method that can be used to balance two conflicting forces: recognizing data from seen classes versus those from unseen ones. We develop a performance metric to characterize such a trade-off and examine the utility of this metric in evaluating various ZSL approaches. Our analysis further shows that there is a large gap between the performance of existing approaches and an upper bound established via idealized semantic embeddings, suggesting that improving class semantic embeddings is vital to GZSL.

Key facts. Cited by 146 papers in the map (data through 7 Oct 2026). First posted on arXiv 13 May 2016.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 49; 2022: 36; 2023: 30; 2024: 14; 2025: 14; 2026: 3.

146 papers.

Sort:

By area:

  1. 2022Conditional Prompt Learning for Vision-Language Modelscited by 1,427
  2. 2021Domain Generalization: A Surveycited by 760
  3. 2021Open-World Semi-Supervised Learningcited by 165
  4. 2023BioCLIP: A Vision Foundation Model for the Tree of Lifecited by 159
  5. 2021Semantic-aware Knowledge Distillation for Few-Shot Class-Incremental Learningcited by 114
  6. 2021Learning Graph Embeddings for Compositional Zero-shot Learningcited by 112
  7. 2022Does CLIP Bind Concepts? Probing Compositionality in Large Image Modelscited by 101
  8. 2021Counterfactual Zero-Shot and Open-Set Visual Recognitioncited by 95
  9. 2021Contrastive Embedding for Generalized Zero-Shot Learningcited by 94
  10. 2021Detecting Human-Object Interaction via Fabricated Compositional Learningcited by 79
  11. 2021Goal-Oriented Gaze Estimation for Zero-Shot Learningcited by 68
  12. 2022Learning to Compose Soft Prompts for Compositional Zero-Shot Learningcited by 66
38 more
  1. 2023A Survey on Open-Vocabulary Detection and Segmentation: Past, Present, and Futurecited by 59
  2. 2021Generative Zero-Shot Learning for Semantic Segmentation of 3D Point Cloudscited by 55
  3. 2022Siamese Contrastive Embedding Network for Compositional Zero-Shot Learningcited by 55
  4. 2022I2MVFormer: Large Language Model Generated Multi-View Document Supervision for Zero-Shot Image Classificationcited by 54
  5. 2021Exploiting a Joint Embedding Space for Generalized Zero-Shot Semantic Segmentationcited by 53
  6. 2021Learning Graph Embeddings for Open World Compositional Zero-Shot Learningcited by 49
  7. 2021Independent Prototype Propagation for Zero-Shot Compositionalitycited by 42
  8. 2021Zero-Shot Learning on 3D Point Cloud Objects and Beyondcited by 38
  9. 2022Learning Domain Invariant Prompt for Vision-Language Modelscited by 35
  10. 2023Learning Attention as Disentangler for Compositional Zero-shot Learningcited by 29
  11. 2023Learning Conditional Attributes for Compositional Zero-Shot Learningcited by 28
  12. 2023Primitive Generation and Semantic-related Alignment for Universal Zero-Shot Segmentationcited by 28
  13. 2022Audio-visual Generalised Zero-shot Learning with Cross-modal Attention and Languagecited by 27
  14. 2022I2DFormer: Learning Image to Document Attention for Zero-Shot Image Classificationcited by 27
  15. 2021Dual Progressive Prototype Network for Generalized Zero-Shot Learningcited by 26
  16. 2021A Survey on Open Set Recognitioncited by 25
  17. 2023Few-shot Class-incremental Learning for Classification and Object Detection: A Surveycited by 25
  18. 2022Learning Invariant Visual Representations for Compositional Zero-Shot Learningcited by 24
  19. 2023Progressive Semantic-Visual Mutual Adaption for Generalized Zero-Shot Learningcited by 24
  20. 2023Zero-Shot Learning by Harnessing Adversarial Samplescited by 24
  21. 2023Language-Driven Anchors for Zero-Shot Adversarial Robustnesscited by 23
  22. 2021Generalized Zero-shot Intent Detection via Commonsense Knowledgecited by 21
  23. 2023See More and Know More: Zero-shot Point Cloud Segmentation via Multi-modal Visual Datacited by 21
  24. 2021Relation-aware Compositional Zero-shot Learning for Attribute-Object Pair Recognitioncited by 19
  25. 2022Attribute Prototype Network for Any-Shot Learningcited by 19
  26. 2022Temporal and cross-modal attention for audio-visual zero-shot learningcited by 19
  27. 2022CheXRelNet: An Anatomy-Aware Model for Tracking Longitudinal Relationships between Chest X-Rayscited by 19
  28. 2024Fine-Grained Side Information Guided Dual-Prompts for Zero-Shot Skeleton Action Recognitioncited by 19
  29. 2023Semantic-Promoted Debiasing and Background Disambiguation for Zero-Shot Instance Segmentationcited by 16
  30. 2023Hierarchical Visual Primitive Experts for Compositional Zero-Shot Learningcited by 16
  31. 2023GIPCOL: Graph-Injected Soft Prompting for Compositional Zero-Shot Learningcited by 16
  32. 2023Image-free Classifier Injection for Zero-Shot Classificationcited by 15
  33. 2021Benchmarking for Biomedical Natural Language Processing Tasks with a Domain Specific ALBERTcited by 14
  34. 2022Improving Zero-Shot Models with Label Distribution Priorscited by 14
  35. 2024AAPL: Adding Attributes to Prompt Learning for Vision-Language Modelscited by 14
  36. 2021Towards Novel Target Discovery Through Open-Set Domain Adaptationcited by 13
  37. 2022On Leveraging Variational Graph Embeddings for Open World Compositional Zero-Shot Learningcited by 13
  38. 2023Beyond Sole Strength: Customized Ensembles for Generalized Vision-Language Modelscited by 13

50 most cited of 146 All 146 (JSON)