mlsanityData to 7 Oct 2026

Zero-Shot Learning -- The Good, the Bad and the Ugly

arXiv 1703.04394 ↗First posted 13 Mar 2017cs.CVcited by 254

Not on the map. Why?

Cited by 37 in Multimodal LLMs / vision-language models, but placed by its own abstract, which didn’t fit.

Abstract (arXiv)

Due to the importance of zero-shot learning, the number of proposed approaches has increased steadily recently. We argue that it is time to take a step back and to analyze the status quo of the area. The purpose of this paper is three-fold. First, given the fact that there is no agreed upon zero-shot learning benchmark, we first define a new benchmark by unifying both the evaluation protocols and data splits. This is an important contribution as published results are often not comparable and sometimes even flawed due to, e.g. pre-training on zero-shot test classes. Second, we compare and analyze a significant number of the state-of-the-art methods in depth, both in the classic zero-shot setting but also in the more realistic generalized zero-shot setting. Finally, we discuss limitations of the current status of the area which can be taken as a basis for advancing it.

Key facts. Cited by 254 papers in the map (data through 7 Oct 2026). First posted on arXiv 13 Mar 2017.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 60; 2022: 48; 2023: 52; 2024: 47; 2025: 30; 2026: 17.

254 papers.

Sort:

By area:

  1. 2022Conditional Prompt Learning for Vision-Language Modelscited by 1,427
  2. 2022Unified Contrastive Learning in Image-Text-Label Spacecited by 194
  3. 2024Generalist Foundation Models from a Multimodal Dataset for 3D Computed Tomographycited by 192
  4. 2021Combined Scaling for Zero-shot Transfer Learningcited by 182
  5. 2021Open-World Semi-Supervised Learningcited by 165
  6. 2021Probabilistic Embeddings for Cross-Modal Retrievalcited by 150
  7. 2023PACO: Parts and Attributes of Common Objectscited by 146
  8. 2022Unified Vision and Language Prompt Learningcited by 145
  9. 2022"This is my unicorn, Fluffy": Personalizing frozen vision-language representationscited by 95
  10. 2021Contrastive Embedding for Generalized Zero-Shot Learningcited by 94
  11. 2022Learning from Few Examples: A Summary of Approaches to Few-Shot Learningcited by 86
  12. 2021Open-Vocabulary Instance Segmentation via Robust Cross-Modal Pseudo-Labelingcited by 84
38 more
  1. 2023Diversity is Definitely Needed: Improving Model-Agnostic Zero-shot Classification via Stable Diffusioncited by 81
  2. 2021ML-Decoder: Scalable and Versatile Classification Headcited by 78
  3. 2023Consistency-guided Prompt Learning for Vision-Language Modelscited by 73
  4. 2021Goal-Oriented Gaze Estimation for Zero-Shot Learningcited by 68
  5. 2021FREE: Feature Refinement for Generalized Zero-Shot Learningcited by 67
  6. 2022Zero Experience Required: Plug & Play Modular Transfer Learning for Semantic Visual Navigationcited by 66
  7. 2023BadCLIP: Trigger-Aware Prompt Learning for Backdoor Attacks on CLIPcited by 63
  8. 2022LASP: Text-to-Text Optimization for Language-Aware Soft Prompting of Vision & Language Modelscited by 58
  9. 2021HSVA: Hierarchical Semantic-Visual Adaptation for Zero-Shot Learningcited by 57
  10. 2021TransZero: Attribute-guided Transformer for Zero-Shot Learningcited by 53
  11. 2023Zero-shot Temporal Relation Extraction with ChatGPTcited by 52
  12. 2023Better Zero-Shot Reasoning with Self-Adaptive Promptingcited by 52
  13. 2022MSDN: Mutually Semantic Distillation Network for Zero-Shot Learningcited by 48
  14. 2023Enhancing CLIP with GPT-4: Harnessing Visual Descriptions as Promptscited by 48
  15. 2022A survey of multimodal deep generative modelscited by 47
  16. 2021SIGN: Spatial-information Incorporated Generative Network for Generalized Zero-shot Semantic Segmentationcited by 41
  17. 2021Zero-Shot Instance Segmentationcited by 40
  18. 2022Novel Class Discovery without Forgettingcited by 39
  19. 2023StyLIP: Multi-Scale Style-Conditioned Prompt Learning for CLIP-based Domain Generalizationcited by 36
  20. 2022Learning Domain Invariant Prompt for Vision-Language Modelscited by 35
  21. 2023Large Language Models Are Zero-Shot Text Classifierscited by 35
  22. 2022StyleT2I: Toward Compositional and High-Fidelity Text-to-Image Synthesiscited by 33
  23. 2022Open-Vocabulary Multi-Label Classification via Multi-Modal Knowledge Transfercited by 33
  24. 2025AGENTSAFE: Benchmarking the Safety of Embodied Agents on Hazardous Instructionscited by 33
  25. 2021All Labels Are Not Created Equal: Enhancing Semi-supervision via Label Grouping and Co-trainingcited by 32
  26. 2023Enhancing CLIP with CLIP: Exploring Pseudolabeling for Limited-Label Prompt Tuningcited by 30
  27. 2022Doubly Right Object Recognition: A Why Prompt for Visual Rationalescited by 29
  28. 2023Upcycling Models under Domain and Category Shiftcited by 29
  29. 2023Learning Attention as Disentangler for Compositional Zero-shot Learningcited by 29
  30. 2023LoGoPrompt: Synthetic Text Images Can Be Good Visual Prompts for Vision-Language Modelscited by 29
  31. 2021SSSE: Efficiently Erasing Samples from Trained Machine Learning Modelscited by 28
  32. 2021TransZero++: Cross Attribute-Guided Transformer for Zero-Shot Learningcited by 28
  33. 2022Open-vocabulary Attribute Detectioncited by 28
  34. 2023Artificial intelligence to advance Earth observation: : A review of models, recent trends, and pathways forwardcited by 28
  35. 2023A Systematic Review of Few-Shot Learning in Medical Imagingcited by 28
  36. 2024Prompt Learning via Meta-Regularizationcited by 26
  37. 2021Multilingual Code-Switching for Zero-Shot Cross-Lingual Intent Prediction and Slot Fillingcited by 25
  38. 2021Segmentation-grounded Scene Graph Generationcited by 25

50 most cited of 254 All 254 (JSON)