mlsanityData to 14 Oct 2026

Domain Adaptation via Prompt Learning

arXiv 2202.06687 ↗First posted 14 Feb 2022cs.CVcited by 128

Not on the map. Why?

Cited by 31 in Multimodal LLMs / vision-language models, but placed by its own abstract, which didn’t fit.

Abstract (arXiv)

Unsupervised domain adaption (UDA) aims to adapt models learned from a well-annotated source domain to a target domain, where only unlabeled samples are given. Current UDA approaches learn domain-invariant features by aligning source and target feature spaces. Such alignments are imposed by constraints such as statistical discrepancy minimization or adversarial training. However, these constraints could lead to the distortion of semantic feature structures and loss of class discriminability. In this paper, we introduce a novel prompt learning paradigm for UDA, named Domain Adaptation via Prompt Learning (DAPL). In contrast to prior works, our approach makes use of pre-trained vision-language models and optimizes only very few parameters. The main idea is to embed domain information into prompts, a form of representations generated from natural language, which is then used to perform classification. This domain information is shared only by images from the same domain, thereby dynamically adapting the classifier according to each domain. By adopting this paradigm, we show that our model not only outperforms previous methods on several cross-domain benchmarks but also is very efficient to train and easy to implement.

Key facts. Cited by 128 papers in the map (data through 14 Oct 2026). Builds on 43 of its 78 references that are in the map. First posted on arXiv 14 Feb 2022.

Builds on

43 of 78 references.

References · 43

  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. 2016SGDR: Stochastic Gradient Descent with Warm Restartscited by 5,045
  7. 2021Prefix-Tuning: Optimizing Continuous Prompts for Generationcited by 3,915
  8. 2021Scaling Up Visual and Vision-Language Representation Learning With Noisy Text Supervisioncited by 3,864
  9. 2021The Power of Scale for Parameter-Efficient Prompt Tuningcited by 3,795
  10. 2021Learning to Prompt for Vision-Language Modelscited by 2,281
  11. 2021Pre-train, Prompt, and Predict: A Systematic Survey of Prompting Methods in Natural Language Processingcited by 2,234
  12. 2019Language Models as Knowledge Bases?cited by 1,936
31 more
  1. 2014Unsupervised Domain Adaptation by Backpropagationcited by 1,917
  2. 2018Moment Matching for Multi-Source Domain Adaptationcited by 1,331
  3. 2015Learning Transferable Features with Deep Adaptation Networkscited by 1,329
  4. 2016Deep CORAL: Correlation Alignment for Deep Domain Adaptationcited by 1,200
  5. 2017Deep Hashing Network for Unsupervised Domain Adaptationcited by 1,188
  6. 2019How Can We Know What Language Models Know?cited by 959
  7. 2021GPT Understands, Toocited by 716
  8. 2017Maximum Classifier Discrepancy for Unsupervised Domain Adaptationcited by 683
  9. 2016Deep Transfer Learning with Joint Adaptation Networkscited by 612
  10. 2014Deep Domain Confusion: Maximizing for Domain Invariancecited by 600
  11. 2017VisDA: The Visual Domain Adaptation Challengecited by 435
  12. 2021Factual Probing Is [MASK]: Learning vs. Learning to Recallcited by 291
  13. 2019Sliced Wasserstein Discrepancy for Unsupervised Domain Adaptationcited by 235
  14. 2017Central Moment Discrepancy (CMD) for Domain-Invariant Representation Learningcited by 192
  15. 2021Knowledgeable Prompt-tuning: Incorporating Knowledge into Prompt Verbalizer for Text Classificationcited by 183
  16. 2020Domain Adaptive Ensemble Learningcited by 156
  17. 2019Transferrable Prototypical Networks for Unsupervised Domain Adaptationcited by 141
  18. 2020Unsupervised Domain Adaptation via Structurally Regularized Deep Clusteringcited by 140
  19. 2020Towards Discriminability and Diversity: Batch Nuclear-norm Maximization under Label Insufficient Situationscited by 133
  20. 2020Gradually Vanishing Bridge for Adversarial Domain Adaptationcited by 130
  21. 2019Domain-Symmetric Networks for Adversarial Domain Adaptationcited by 120
  22. 2020Convolutional Networks with Dense Connectivitycited by 98
  23. 2019E-BERT: Efficient-Yet-Effective Entity Embeddings for BERTcited by 96
  24. 2020A Review of Single-Source Deep Unsupervised Visual Domain Adaptationcited by 96
  25. 2021Cross-Domain Gradient Discrepancy Minimization for Unsupervised Domain Adaptationcited by 67
  26. 2020Learning Disentangled Semantic Representation for Domain Adaptationcited by 55
  27. 2019Unsupervised Domain Adaptation via Structured Prediction Based Selective Pseudo-Labelingcited by 53
  28. 2020Domain Conditioned Adaptation Networkcited by 43
  29. 2019Transfer Learning with Dynamic Distribution Adaptationcited by 40
  30. 2021Aligning Correlation Information for Domain Adaptation in Action Recognitioncited by 30
  31. 2018Unsupervised Domain Adaptation with Adversarial Residual Transform Networkscited by 14

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2022: 9; 2023: 31; 2024: 45; 2025: 29; 2026: 14.

128 papers.

Sort:

By area:

  1. 2023Domain Specialization as the Key to Make Large Language Models Disruptive: A Comprehensive Surveycited by 135
  2. 2023LoCoOp: Few-Shot Out-of-Distribution Detection via Prompt Learningcited by 107
  3. 2022Decorate the Newcomers: Visual Domain Prompt for Continual Test Time Adaptationcited by 98
  4. 2022Visual Prompt Tuning for Test-time Domain Adaptationcited by 97
  5. 2023PromptMRG: Diagnosis-Driven Prompts for Medical Report Generationcited by 95
  6. 2023Towards Large-scale 3D Representation Learning with Multi-dataset Point Prompt Trainingcited by 86
  7. 2024A Survey of Attacks on Large Vision-Language Models: Resources, Advances, and Future Trendscited by 84
  8. 2022Visual Prompt Tuning for Generative Transfer Learningcited by 75
  9. 2024PromptKD: Unsupervised Prompt Distillation for Vision-Language Modelscited by 72
  10. 2022Learning to Compose Soft Prompts for Compositional Zero-Shot Learningcited by 67
  11. 2023AD-CLIP: Adapting Domains in Prompt Space Using CLIPcited by 62
  12. 2023Source-Free Domain Adaptation with Frozen Multimodal Foundation Modelcited by 55
38 more
  1. 2022Bayesian Prompt Learning for Image-Language Model Generalizationcited by 51
  2. 2022Texts as Images in Prompt Tuning for Multi-Label Image Recognitioncited by 51
  3. 2023See, Think, Confirm: Interactive Prompting Between Vision and Language Models for Knowledge-based Visual Reasoningcited by 51
  4. 2023Incorporating Structured Representations into Pretrained Vision & Language Models Using Scene Graphscited by 39
  5. 2024DPCore: Dynamic Prompt Coreset for Continual Test-Time Adaptationcited by 33
  6. 2024Domain-Agnostic Mutual Prompting for Unsupervised Domain Adaptationcited by 32
  7. 2023Enhancing CLIP with CLIP: Exploring Pseudolabeling for Limited-Label Prompt Tuningcited by 30
  8. 2024Unified Language-driven Zero-shot Domain Adaptationcited by 30
  9. 2023Exploring Sparse Visual Prompt for Domain Adaptive Dense Predictioncited by 28
  10. 2023DeltaEdit: Exploring Text-free Training for Text-Driven Image Manipulationcited by 27
  11. 2023Zero-shot Generative Model Adaptation via Image-specific Prompt Learningcited by 27
  12. 2022Multi-Prompt Alignment for Multi-Source Unsupervised Domain Adaptationcited by 25
  13. 2023LeftRefill: Filling Right Canvas based on Left Reference through Generalized Text-to-Image Diffusion Modelcited by 25
  14. 2024Soft Prompt Generation for Domain Generalizationcited by 24
  15. 2025Advances in Multimodal Adaptation and Generalization: From Traditional Approaches to Foundation Modelscited by 23
  16. 2023Domain-Controlled Prompt Learningcited by 22
  17. 2023Learning Expressive Prompting With Residuals for Vision Transformerscited by 21
  18. 2024Proxy Denoising for Source-Free Domain Adaptationcited by 21
  19. 2024Candidate Pseudolabel Learning: Enhancing Vision-Language Models by Prompt Tuning with Unlabeled Datacited by 20
  20. 2023PromptFusion: Decoupling Stability and Plasticity for Continual Learningcited by 17
  21. 2024OT-VP: Optimal Transport-guided Visual Prompting for Test-Time Adaptationcited by 17
  22. 2023TransHP: Image Classification with Hierarchical Promptingcited by 16
  23. 2025CLIP-Powered Domain Generalization and Domain Adaptation: A Comprehensive Surveycited by 15
  24. 2023EZ-CLIP: Efficient Zeroshot Video Action Recognitioncited by 14
  25. 2024PIN: Positional Insert Unlocks Object Localisation Abilities in VLMscited by 14
  26. 2025Handling Out-of-Distribution Data: A Surveycited by 14
  27. 2024Split to Merge: Unifying Separated Modalities for Unsupervised Domain Adaptationcited by 13
  28. 2024CoDA: Instructive Chain-of-Domain Adaptation with Severity-Aware Visual Prompt Tuningcited by 13
  29. 2023Patch-Prompt Aligned Bayesian Prompt Tuning for Vision-Language Modelscited by 12
  30. 2023A Systematic Survey of Prompt Engineering on Vision-Language Foundation Modelscited by 12
  31. 2024Semi-Supervised Semantic Segmentation Based on Pseudo-Labels: A Surveycited by 12
  32. 2024Unsupervised Domain Adaption Harnessing Vision-Language Pre-trainingcited by 12
  33. 2022Fine-grained Retrieval Prompt Tuningcited by 11
  34. 2023Open-Set Domain Adaptation with Visual-Language Foundation Modelscited by 10
  35. 2023CLAP: Isolating Content from Style through Contrastive Learning with Augmented Promptscited by 10
  36. 2025Large Self-Supervised Models Bridge the Gap in Domain Adaptive Object Detectioncited by 9
  37. 2024HCVP: Leveraging Hierarchical Contrastive Visual Prompt for Domain Generalizationcited by 8
  38. 2024Enhancing Domain Adaptation through Prompt Gradient Alignmentcited by 8

50 most cited of 128 All 128 (JSON)

Similar, not cited

Close in wording, no citation either way

  1. 2023Prompt-based Distribution Alignment for Unsupervised Domain Adaptation
  2. 2022PODA: Prompt-driven Zero-shot Domain Adaptation
  3. 2022Learning Domain Invariant Prompt for Vision-Language Models
  4. 2023Prompt Ensemble Self-training for Open-Vocabulary Domain Adaptation
  5. 2023Learning to Prompt Your Domain for Vision-Language Models
  6. 2025Latent Domain Prompt Learning for Vision-Language Models
  7. 2024Transitive Vision-Language Prompt Learning for Domain Generalization
  8. 2025C-DGPA: Class-Centric Dual-Alignment Generative Prompt Adaptation