mlsanityData to 14 Oct 2026

DualCoOp: Fast Adaptation to Multi-Label Recognition with Limited Annotations

arXiv 2206.09541 ↗First posted 20 Jun 2022cs.CVcited by 102

Not on the map. Why?

Cited by 45 in Multimodal LLMs / vision-language models, but placed by its own abstract, which didn’t fit.

Abstract (arXiv)

Solving multi-label recognition (MLR) for images in the low-label regime is a challenging task with many real-world applications. Recent work learns an alignment between textual and visual spaces to compensate for insufficient image labels, but loses accuracy because of the limited amount of available MLR annotations. In this work, we utilize the strong alignment of textual and visual features pretrained with millions of auxiliary image-text pairs and propose Dual Context Optimization (DualCoOp) as a unified framework for partial-label MLR and zero-shot MLR. DualCoOp encodes positive and negative contexts with class names as part of the linguistic input (i.e. prompts). Since DualCoOp only introduces a very light learnable overhead upon the pretrained vision-language framework, it can quickly adapt to multi-label recognition tasks that have limited annotations and even unseen classes. Experiments on standard multi-label recognition benchmarks across two challenging low-label settings demonstrate the advantages of our approach over state-of-the-art methods.

Key facts. Cited by 102 papers in the map (data through 14 Oct 2026). Builds on 52 of its 87 references that are in the map. First posted on arXiv 20 Jun 2022.

Builds on

52 of 87 references.

References · 52

  1. 2017Attention Is All You Needcited by 60,361
  2. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  3. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,744
  4. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 30,186
  5. 2014Microsoft COCO: Common Objects in Contextcited by 17,608
  6. 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,364
  7. 2021Swin Transformer: Hierarchical Vision Transformer using Shifted Windowscited by 12,139
  8. 2021Prefix-Tuning: Optimizing Continuous Prompts for Generationcited by 3,915
  9. 2021Scaling Up Visual and Vision-Language Representation Learning With Noisy Text Supervisioncited by 3,864
  10. 2021The Power of Scale for Parameter-Efficient Prompt Tuningcited by 3,795
  11. 2016Visual Genome: Connecting Language and Vision Using Crowdsourced Dense Image Annotationscited by 2,656
  12. 2021Learning to Prompt for Vision-Language Modelscited by 2,281
38 more
  1. 2022Conditional Prompt Learning for Vision-Language Modelscited by 1,433
  2. 2021CLIP-Adapter: Better Vision-Language Models with Feature Adapterscited by 1,026
  3. 2017Revisiting Unreasonable Effectiveness of Data in Deep Learning Eracited by 919
  4. 2021Robust fine-tuning of zero-shot modelscited by 797
  5. 2018Exploring the Limits of Weakly Supervised Pretrainingcited by 605
  6. 2018The Open Images Dataset V4: Unified image classification, object detection, and visual relationship detection at scalecited by 544
  7. 2021Tip-Adapter: Training-free CLIP-Adapter for Better Vision-Language Modelingcited by 431
  8. 2020Asymmetric Loss For Multi-Label Classificationcited by 381
  9. 2019Multi-Label Image Recognition with Graph Convolutional Networkscited by 322
  10. 2021Prompting Visual-Language Models for Efficient Video Understandingcited by 310
  11. 2018Bilinear Attention Networkscited by 280
  12. 2022Prompt Distribution Learningcited by 235
  13. 2016CNN-RNN: A Unified Framework for Multi-label Image Classificationcited by 190
  14. 2018Zero-Shot Object Detectioncited by 189
  15. 2021CPT: Colorful Prompt Tuning for Pre-trained Vision-Language Modelscited by 183
  16. 2015Label-Embedding for Image Classificationcited by 165
  17. 2015Learning Visual Features from Large Weakly Supervised Datacited by 165
  18. 2013Zero-Shot Learning by Convex Combination of Semantic Embeddingscited by 135
  19. 2022Unsupervised Prompt Learning for Vision-Language Modelscited by 127
  20. 2019Learning a Deep ConvNet for Multi-label Classification with Partial Labelscited by 124
  21. 2019Learning Semantic-Specific Graph Representation for Multi-Label Image Recognitioncited by 116
  22. 2016Learning Visual N-Grams from Web Datacited by 95
  23. 2017Learning Spatial Regularization with Image-level Supervisions for Multi-label Image Classificationcited by 85
  24. 2017Multi-label Image Recognition by Recurrently Discovering Attentional Regionscited by 83
  25. 2017Multi-Label Zero-Shot Learning with Structured Knowledge Graphscited by 72
  26. 2020Knowledge-Guided Multi-Label Few-Shot Learning for General Image Recognitioncited by 69
  27. 2019Multi-Label Classification with Label Graph Superimposingcited by 65
  28. 2015Seeing through the Human Reporting Bias: Visual Classifiers from Noisy Human-Centric Labelscited by 64
  29. 2018Deep Imbalanced Attribute Classification using Visual Attention Aggregationcited by 56
  30. 2021Residual Attention: A Simple but Effective Method for Multi-Label Recognitioncited by 52
  31. 2019Orderless Recurrent Models for Multi-label Classificationcited by 46
  32. 2021Structured Semantic Transfer for Multi-Label Recognition with Partial Labelscited by 41
  33. 2018Multi-Label Image Classification via Knowledge Distillation from Weakly-Supervised Detectioncited by 37
  34. 2022Semantic-Aware Representation Blending for Multi-Label Image Recognition with Partial Labelscited by 29
  35. 2021Discriminative Region-based Multi-Label Zero-Shot Learningcited by 27
  36. 2021Semantic Diversity Learning for Zero-Shot Multi-label Classificationcited by 24
  37. 2016Fast Zero-Shot Image Taggingcited by 21
  38. 2021Generative Multi-Label Zero-Shot Learningcited by 19

50 most cited of 52 All 52 (JSON)

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2022: 6; 2023: 28; 2024: 33; 2025: 29; 2026: 6.

102 papers.

Sort:

By area:

  1. 2023Vision-Language Models for Vision Tasks: A Surveycited by 839
  2. 2023AnomalyCLIP: Object-agnostic Prompt Learning for Zero-shot Anomaly Detectioncited by 271
  3. 2022Unified Vision and Language Prompt Learningcited by 148
  4. 2023DDCoT: Duty-Distinct Chain-of-Thought Prompting for Multimodal Reasoning in Language Modelscited by 128
  5. 2023LoCoOp: Few-Shot Out-of-Distribution Detection via Prompt Learningcited by 107
  6. 2023A Closer Look at the Explainability of Contrastive Language-Image Pre-trainingcited by 96
  7. 2023Vita-CLIP: Video and text adaptive CLIP via Multimodal Promptingcited by 91
  8. 2023Open-Set Image Tagging with Multi-Grained Text Supervisioncited by 67
  9. 2023BadCLIP: Trigger-Aware Prompt Learning for Backdoor Attacks on CLIPcited by 67
  10. 2023Sentence-level Prompts Benefit Composed Image Retrievalcited by 59
  11. 2022Bayesian Prompt Learning for Image-Language Model Generalizationcited by 51
  12. 2022Texts as Images in Prompt Tuning for Multi-Label Image Recognitioncited by 51
38 more
  1. 2024Learning Transferable Negative Prompts for Out-of-Distribution Detectioncited by 43
  2. 2022Understanding and Mitigating Overfitting in Prompt Tuning for Vision-Language Modelscited by 40
  3. 2023CLIP in Medical Imaging: A Surveycited by 40
  4. 2025Rethinking Vision-Language Model in Face Forensics: Multi-Modal Interpretable Forged Face Detectorcited by 40
  5. 2023CDUL: CLIP-Driven Unsupervised Learning for Multi-Label Image Classificationcited by 39
  6. 2023GL-MCM: Global and Local Maximum Concept Matching for Zero-Shot Out-of-Distribution Detectioncited by 36
  7. 2023Visual Tuningcited by 34
  8. 2022Open-Vocabulary Multi-Label Classification via Multi-Modal Knowledge Transfercited by 33
  9. 2023Distilling Large Vision-Language Model with Out-of-Distribution Generalizabilitycited by 33
  10. 2023Enhancing CLIP with CLIP: Exploring Pseudolabeling for Limited-Label Prompt Tuningcited by 30
  11. 2024GalLoP: Learning Global and Local Prompts for Vision-Language Modelscited by 29
  12. 2024PointAD: Comprehending 3D Anomalies from Points and Pixels for Zero-shot 3D Anomaly Detectioncited by 29
  13. 2023DIME-FM: DIstilling Multimodal and Efficient Foundation Modelscited by 28
  14. 2023Exploring Structured Semantic Prior for Multi Label Recognition with Incomplete Labelscited by 24
  15. 2023Defense-Prefix for Preventing Typographic Attacks on CLIPcited by 24
  16. 2025Advances in Multimodal Adaptation and Generalization: From Traditional Approaches to Foundation Modelscited by 23
  17. 2023DualCoOp++: Fast and Effective Adaptation to Multi-Label Recognition with Limited Annotationscited by 22
  18. 2023Why Is Prompt Tuning for Vision-Language Models Robust to Noisy Labels?cited by 21
  19. 2023TagCLIP: A Local-to-Global Framework to Enhance Open-Vocabulary Multi-Label Classification of CLIP Without Trainingcited by 19
  20. 2024Vision-Language Models are Strong Noisy Label Detectorscited by 16
  21. 2025Keeping Yourself is Important in Downstream Tuning Multimodal Large Language Modelcited by 16
  22. 2023LMPT: Prompt Tuning with Class-Specific Embedding Loss for Long-tailed Multi-Label Visual Recognitioncited by 15
  23. 2024Self-Calibrated Tuning of Vision-Language Models for Out-of-Distribution Detectioncited by 15
  24. 2025CLIP-Powered Domain Generalization and Domain Adaptation: A Comprehensive Surveycited by 15
  25. 2024TAI++: Text as Image for Multi-Label Image Classification by Co-Learning Transferable Promptcited by 14
  26. 2022Prompt Tuning with Soft Context Sharing for Vision-Language Modelscited by 13
  27. 2024Learning to Prompt Segment Anything Modelscited by 13
  28. 2023Patch-Prompt Aligned Bayesian Prompt Tuning for Vision-Language Modelscited by 12
  29. 2023Vision-Language Pseudo-Labels for Single-Positive Multi-Label Learningcited by 10
  30. 2025Long-tailed Recognition with Model Rebalancingcited by 10
  31. 2024Text-Region Matching for Multi-Label Image Recognition with Missing Labelscited by 9
  32. 2025Advancing Reliable Test-Time Adaptation of Vision-Language Models under Visual Variationscited by 9
  33. 2024Data-free Multi-label Image Recognition via LLM-powered Prompt Tuningcited by 8
  34. 2024Enhancing Vision-Language Few-Shot Adaptation with Negative Learningcited by 8
  35. 2023Positive Label Is All You Need for Multi-Label Classificationcited by 7
  36. 2024Open-Vocabulary Temporal Action Localization using Multimodal Guidancecited by 7
  37. 2023Black-Box Tuning of Vision-Language Models with Effective Gradient Approximationcited by 6
  38. 2024Improving Multi-label Recognition using Class Co-Occurrence Probabilitiescited by 6

50 most cited of 102 All 102 (JSON)