mlsanityData to 14 Oct 2026

PODA: Prompt-driven Zero-shot Domain Adaptation

arXiv 2212.03241 ↗First posted 6 Dec 2022cs.CV cs.LGcited by 60

Not on the map. Why?

Abstract (arXiv)

Domain adaptation has been vastly investigated in computer vision but still requires access to target images at train time, which might be intractable in some uncommon conditions. In this paper, we propose the task of `Prompt-driven Zero-shot Domain Adaptation', where we adapt a model trained on a source domain using only a general description in natural language of the target domain, i.e., a prompt. First, we leverage a pretrained contrastive vision-language model (CLIP) to optimize affine transformations of source features, steering them towards the target text embedding while preserving their content and semantics. To achieve this, we propose Prompt-driven Instance Normalization (PIN). Second, we show that these prompt-driven augmentations can be used to perform zero-shot domain adaptation for semantic segmentation. Experiments demonstrate that our method significantly outperforms CLIP-based style transfer baselines on several datasets for the downstream task at hand, even surpassing one-shot unsupervised domain adaptation. A similar boost is observed on object detection and image classification. The code is available at https://github.com/astra-vision/PODA .

Key facts. Cited by 60 papers in the map (data through 14 Oct 2026). Builds on 50 of its 66 references that are in the map. First posted on arXiv 6 Dec 2022.

Builds on

50 of 66 references.

References · 50

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,744
  3. 2018A Style-Based Generator Architecture for Generative Adversarial Networkscited by 6,013
  4. 2016Feature Pyramid Networks for Object Detectioncited by 5,036
  5. 2014Fully Convolutional Networks for Semantic Segmentationcited by 4,859
  6. 2016The Cityscapes Dataset for Semantic Urban Scene Understandingcited by 4,444
  7. 2021On the Opportunities and Risks of Foundation Modelscited by 4,033
  8. 2021Scaling Up Visual and Vision-Language Representation Learning With Noisy Text Supervisioncited by 3,864
  9. 2020Taming Transformers for High-Resolution Image Synthesiscited by 3,253
  10. 2016DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFscited by 3,241
  11. 2018Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentationcited by 3,223
  12. 2015Domain-Adversarial Training of Neural Networkscited by 3,044
38 more
  1. 2016Pyramid Scene Parsing Networkcited by 2,479
  2. 2017Arbitrary Style Transfer in Real-time with Adaptive Instance Normalizationcited by 2,010
  3. 2019Invariant Risk Minimizationcited by 1,854
  4. 2021Align before Fuse: Vision and Language Representation Learning with Momentum Distillationcited by 1,619
  5. 2019Deep High-Resolution Representation Learning for Visual Recognitioncited by 1,420
  6. 2019Can You Trust Your Model's Uncertainty? Evaluating Predictive Uncertainty Under Dataset Shiftcited by 1,287
  7. 2016Deep CORAL: Correlation Alignment for Deep Domain Adaptationcited by 1,200
  8. 2017CyCADA: Cycle-Consistent Adversarial Domain Adaptationcited by 1,082
  9. 2020In Search of Lost Domain Generalizationcited by 1,054
  10. 2021StyleCLIP: Text-Driven Manipulation of StyleGAN Imagerycited by 991
  11. 2016Playing for Data: Ground Truth from Computer Gamescited by 818
  12. 2022Language-driven Semantic Segmentationcited by 717
  13. 2019Panoptic Feature Pyramid Networkscited by 645
  14. 2018ADVENT: Adversarial Entropy Minimization for Domain Adaptation in Semantic Segmentationcited by 623
  15. 2018Learning to Adapt Structured Output Space for Semantic Segmentationcited by 584
  16. 2021Extract Free Dense Labels from CLIPcited by 583
  17. 2020FDA: Fourier Domain Adaptation for Semantic Segmentationcited by 541
  18. 2019Confidence Regularized Self-Trainingcited by 419
  19. 2017Semantic Foggy Scene Understanding with Synthetic Datacited by 403
  20. 2019Panoptic-DeepLabcited by 363
  21. 2019Bidirectional Learning for Domain Adaptation of Semantic Segmentationcited by 308
  22. 2022Simple Open-Vocabulary Object Detection with Vision Transformerscited by 305
  23. 2017ICNet for Real-Time Semantic Segmentation on High-Resolution Imagescited by 261
  24. 2021CLIPstyler: Image Style Transfer with a Single Text Conditioncited by 203
  25. 2020Unsupervised Intra-domain Adaptation for Semantic Segmentation through Self-Supervisioncited by 198
  26. 2021StyleGAN-NADA: CLIP-Guided Domain Adaptation of Image Generatorscited by 164
  27. 2022Data Determines Distributional Robustness in Contrastive Language Image Pre-training (CLIP)cited by 138
  28. 2018Dark Model Adaptation: Semantic Image Segmentation from Daytime to Nighttimecited by 122
  29. 2021You Only Look One-level Featurecited by 116
  30. 2022"This is my unicorn, Fluffy": Personalizing frozen vision-language representationscited by 95
  31. 2020Adversarial Style Mining for One-Shot Unsupervised Domain Adaptationcited by 64
  32. 2021Zero-Shot Day-Night Domain Adaptation with a Physics Priorcited by 47
  33. 2021Seeking Similarities over Differences: Similarity-based Domain Alignment for Adaptive Object Detectioncited by 45
  34. 2020Night-time Scene Parsing with a Large Real Datasetcited by 37
  35. 2022FlexIT: Towards Flexible Semantic Image Translationcited by 28
  36. 2017Deep Domain Adaptation by Geodesic Distance Minimizationcited by 17
  37. 2021Style Mixing and Patchwise Prototypical Matching for One-Shot Unsupervised Domain Adaptive Semantic Segmentationcited by 15
  38. 2021ManiFest: Manifold Deformation for Few-shot Image Translationcited by 6

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2023: 8; 2024: 24; 2025: 19; 2026: 9.

60 papers.

Sort:

By area:

  1. 2023Domain Specialization as the Key to Make Large Language Models Disruptive: A Comprehensive Surveycited by 135
  2. 2023Collaborating Foundation Models for Domain Generalized Semantic Segmentationcited by 34
  3. 2024Unified Language-driven Zero-shot Domain Adaptationcited by 30
  4. 2024Improving Single Domain-Generalized Object Detection: A Focus on Diversification and Alignmentcited by 29
  5. 2023A Simple Recipe for Language-guided Domain Generalized Segmentationcited by 28
  6. 2024Attention Prompting on Image for Large Vision-Language Modelscited by 23
  7. 2025Advances in Multimodal Adaptation and Generalization: From Traditional Approaches to Foundation Modelscited by 23
  8. 2023Strong but simple: A Baseline for Domain Generalized Dense Perception by CLIP-based Transfer Learningcited by 20
  9. 2023Learning Domain-Aware Detection Head with Prompt Tuningcited by 18
  10. 2025FisherTune: Fisher-Guided Robust Tuning of Vision Foundation Models for Domain Generalized Segmentationcited by 16
  11. 2025Learning to Adapt Frozen CLIP for Few-Shot Test-Time Domain Adaptationcited by 14
  12. 2024CoDA: Instructive Chain-of-Domain Adaptation with Severity-Aware Visual Prompt Tuningcited by 13
38 more
  1. 2024Prompt-Driven Contrastive Learning for Transferable Adversarial Attackscited by 9
  2. 2025Large Self-Supervised Models Bridge the Gap in Domain Adaptive Object Detectioncited by 9
  3. 2024DA-Ada: Learning Domain-Aware Adapter for Domain Adaptive Object Detectioncited by 8
  4. 2024Zero-Shot Medical Phrase Grounding with Off-the-shelf Diffusion Modelscited by 7
  5. 2025Generalizing vision-language models to novel domains: A comprehensive surveycited by 7
  6. 2025CoPT: Unsupervised Domain Adaptive Segmentation using Domain-Agnostic Text Embeddingscited by 7
  7. 2024EAGLE: Efficient Adaptive Geometry-based Learning in Cross-view Understandingcited by 6
  8. 2025Style Evolving along Chain-of-Thought for Unknown-Domain Object Detectioncited by 6
  9. 2025Style Transfer with Diffusion Models for Synthetic-to-Real Domain Adaptationcited by 6
  10. 2024Phrase Grounding-based Style Transfer for Single-Domain Generalized Object Detectioncited by 5
  11. 2024ZoDi: Zero-Shot Domain Adaptation with Diffusion-Based Image Transfercited by 5
  12. 2023STARS: Zero-shot Sim-to-Real Transfer for Segmentation of Shipwrecks in Sonar Imagerycited by 4
  13. 2024Language-Guided Instance-Aware Domain-Adaptive Panoptic Segmentationcited by 4
  14. 2024Feature Augmentation based Test-Time Adaptationcited by 4
  15. 2025UPRE: Zero-Shot Domain Adaptation for Object Detection via Unified Prompt and Representation Enhancementcited by 4
  16. 2024LatteCLIP: Unsupervised CLIP Fine-Tuning via LMM-Synthetic Textscited by 3
  17. 2025Zero Shot Domain Adaptive Semantic Segmentation by Synthetic Data Generation and Progressive Adaptationcited by 3
  18. 2024VeCAF: Vision-language Collaborative Active Finetuning with Training Objective Awarenesscited by 2
  19. 2024WildFit: Autonomous In-situ Model Adaptation for Resource-Constrained IoT Systemscited by 2
  20. 2024UMFC: Unsupervised Multi-Domain Feature Calibration for Vision-Language Modelscited by 2
  21. 2023Can Out-of-Domain data help to Learn Domain-Specific Prompts for Multimodal Misinformation Detection?cited by 1
  22. 2023Beyond Entropy: Style Transfer Guided Single Image Continual Test-Time Adaptationcited by 1
  23. 2024Weatherproofing Retrieval for Localization with Generative AI and Geometric Consistencycited by 1
  24. 2024Ayn: A Tiny yet Competitive Indian Legal Language Model Pretrained from Scratchcited by 1
  25. 2024Enhancing Vision-Language Models Generalization via Diversity-Driven Novel Feature Synthesiscited by 1
  26. 2024LARE: Latent Augmentation using Regional Embedding with Vision-Language Modelcited by 1
  27. 2024Domain Adaptation with a Single Vision-Language Embeddingcited by 1
  28. 2025LangDA: Building Context-Awareness via Language for Domain Adaptive Semantic Segmentationcited by 1
  29. 2025Prmpt2Adpt: Prompt-Based Zero-Shot Domain Adaptation for Resource-Constrained Environmentscited by 1
  30. 20253D Test-time Adaptation via Graph Spectral Driven Point Shiftcited by 1
  31. 2025Towards Single-Source Domain Generalized Object Detection via Causal Visual Promptscited by 1
  32. 2025Prompt-Driven Domain Adaptation for End-to-End Autonomous Driving via In-Context RLcited by 1
  33. 2026Unlocking Few-Shot Capabilities in LVLMs via Prompt Conditioning and Head Selectioncited by 1
  34. 2024Can Better Text Semantics in Prompt Tuning Improve VLM Generalization?cited by 0
  35. 2024Zero-shot domain adaptation based on dual-level mix and contrastcited by 0
  36. 2024A Study on Unsupervised Domain Adaptation for Semantic Segmentation in the Era of Vision-Language Modelscited by 0
  37. 2025Language-Driven Dual Style Mixing for Single-Domain Generalized Object Detectioncited by 0
  38. 2025Collaborative Editable Modelcited by 0

50 most cited of 60 All 60 (JSON)

Similar, not cited

Close in wording, no citation either way

  1. 2024Rethinking Domain Adaptation and Generalization in the Era of CLIP
  2. 2022Domain Adaptation via Prompt Learning
  3. 2024Domain-Agnostic Mutual Prompting for Unsupervised Domain Adaptation
  4. 2023AD-CLIP: Adapting Domains in Prompt Space Using CLIP
  5. 2025Open Set Domain Adaptation with Vision-language models via Gradient-aware Separation
  6. 2024Enhancing Domain Adaptation through Prompt Gradient Alignment
  7. 2022Learning Domain Invariant Prompt for Vision-Language Models
  8. 2025Prompt-OT: An Optimal Transport Regularization Paradigm for Knowledge Preservation in Vision-Language Model Adaptation