mlsanityData to 7 Oct 2026

Using Language to Extend to Unseen Domains

arXiv 2210.09520 ↗First posted 18 Oct 2022cs.CVcited by 34

Not on the map. Why?

Abstract (arXiv)

It is expensive to collect training data for every possible domain that a vision model may encounter when deployed. We instead consider how simply verbalizing the training domain (e.g. "photos of birds") as well as domains we want to extend to but do not have data for (e.g. "paintings of birds") can improve robustness. Using a multimodal model with a joint image and language embedding space, our method LADS learns a transformation of the image embeddings from the training domain to each unseen test domain, while preserving task relevant information. Without using any images from the unseen test domain, we show that over the extended domain containing both training and unseen test domains, LADS outperforms standard fine-tuning and ensemble approaches over a suite of four benchmarks targeting domain adaptation and dataset bias.

Key facts. Cited by 34 papers in the map (data through 7 Oct 2026). Builds on 33 of its 42 references that are in the map. First posted on arXiv 18 Oct 2022.

Builds on

33 of 42 references.

References · 33

  1. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,456
  2. 2022Hierarchical Text-Conditional Image Generation with CLIP Latentscited by 6,539
  3. 2022Flamingo: a Visual Language Model for Few-Shot Learningcited by 4,337
  4. 2021Scaling Up Visual and Vision-Language Representation Learning With Noisy Text Supervisioncited by 3,848
  5. 2020Taming Transformers for High-Resolution Image Synthesiscited by 3,229
  6. 2019Benchmarking Neural Network Robustness to Common Corruptions and Perturbationscited by 2,857
  7. 2014Unsupervised Domain Adaptation by Backpropagationcited by 1,906
  8. 2019Invariant Risk Minimizationcited by 1,832
  9. 2019Do ImageNet Classifiers Generalize to ImageNet?cited by 1,507
  10. 2019Natural Adversarial Examplescited by 1,401
  11. 2020WILDS: A Benchmark of in-the-Wild Distribution Shiftscited by 1,366
  12. 2018Moment Matching for Multi-Source Domain Adaptationcited by 1,327
21 more
  1. 2017Deep Hashing Network for Unsupervised Domain Adaptationcited by 1,181
  2. 2020In Search of Lost Domain Generalizationcited by 1,042
  3. 2021StyleCLIP: Text-Driven Manipulation of StyleGAN Imagerycited by 990
  4. 2021Robust fine-tuning of zero-shot modelscited by 785
  5. 2022Fine-Tuning can Distort Pretrained Features and Underperform Out-of-Distributioncited by 722
  6. 2017Maximum Classifier Discrepancy for Unsupervised Domain Adaptationcited by 682
  7. 2022VQGAN-CLIP: Open Domain Image Generation and Editing with Natural Language Guidancecited by 285
  8. 2018Learning Not to Learn: Training Deep Neural Networks with Biased Datacited by 255
  9. 2018Women also Snowboard: Overcoming Bias in Captioning Modelscited by 236
  10. 2015Simultaneous Deep Transfer Across Domains and Taskscited by 205
  11. 2017Generate To Adapt: Aligning Domains using Generative Adversarial Networkscited by 183
  12. 2018Tell Me Where to Look: Guided Attention Inference Networkcited by 168
  13. 2019Interpretations are useful: penalizing explanations to align neural networks with prior knowledgecited by 144
  14. 2019Why Can't I Dance in the Mall? Learning to Mitigate Scene Bias in Action Recognitioncited by 117
  15. 2017Few-Shot Adversarial Domain Adaptationcited by 111
  16. 2020Rewriting a Deep Generative Modelcited by 105
  17. 2021Editing a classifier by rewriting its prediction rulescited by 64
  18. 2022On Guiding Visual Attention with Language Specificationcited by 30
  19. 2020Contrastive Examples for Addressing the Tyranny of the Majoritycited by 21
  20. 2020Adversarial Learning for Zero-shot Domain Adaptationcited by 7
  21. 2021Multi-source Few-shot Domain Adaptationcited by 7

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 1; 2023: 10; 2024: 14; 2025: 8; 2026: 1.

34 papers.

Sort:

By area:

  1. 2022Fake it till you make it: Learning transferable representations from synthetic ImageNet clonescited by 171
  2. 2023Diversify Your Vision Datasets with Automatic Diffusion-Based Augmentationcited by 100
  3. 2023Waffling around for Performance: Visual Classification with Random Words and Broad Conceptscited by 100
  4. 2023PromptStyler: Prompt-driven Style Generation for Source-free Domain Generalizationcited by 59
  5. 2025Advances in Multimodal Adaptation and Generalization: From Traditional Approaches to Foundation Modelscited by 23
  6. 2024LanDA: Language-Guided Multi-Source Domain Adaptationcited by 13
  7. 2023Interactive Data Synthesis for Systematic Vision Adaptation via LLMs-AIGCs Collaborationcited by 12
  8. 2023Where Does My Model Underperform? A Human Evaluation of Slice Discovery Algorithmscited by 9
  9. 2024Prompt-Driven Contrastive Learning for Transferable Adversarial Attackscited by 9
  10. 2023GeNIe: Generative Hard Negative Images Through Diffusioncited by 8
  11. 2024Clarify: Improving Model Robustness With Natural Language Correctionscited by 8
  12. 2024DPStyler: Dynamic PromptStyler for Source-Free Domain Generalizationcited by 6
22 more
  1. 2023ASPIRE: Language-Guided Data Augmentation for Improving Robustness Against Spurious Correlationscited by 5
  2. 2024Lightweight Unsupervised Federated Learning with Pretrained Vision Language Modelcited by 5
  3. 2023Coping with Change: Learning Invariant and Minimum Sufficient Representations for Fine-Grained Visual Categorizationcited by 4
  4. 2024Tell, Don't Show!: Language Guidance Eases Transfer Across Domains in Images and Videoscited by 4
  5. 2024Knowledge-Enhanced Facial Expression Recognition with Emotional-to-Neutral Transformationcited by 3
  6. 2024UMFC: Unsupervised Multi-Domain Feature Calibration for Vision-Language Modelscited by 2
  7. 2024MaskMedPaint: Masked Medical Image Inpainting with Diffusion Models for Mitigation of Spurious Correlationscited by 2
  8. 2025Explaining Domain Shifts in Language: Concept erasing for Interpretable Image Classificationcited by 2
  9. 2023Language-assisted Vision Model Debugger: A Sample-Free Approach to Finding and Fixing Bugscited by 1
  10. 2024Cross-modality debiasing: using language to mitigate sub-population shifts in imagingcited by 1
  11. 2024WIDIn: Wording Image for Domain-Invariant Representation in Single-Source Domain Generalizationcited by 1
  12. 2024LARE: Latent Augmentation using Regional Embedding with Vision-Language Modelcited by 1
  13. 2025An Empirical Study of Validating Synthetic Data for Text-Based Person Retrievalcited by 1
  14. 2023LaViP:Language-Grounded Visual Promptscited by 0
  15. 2024SAFLEX: Self-Adaptive Augmentation via Feature Label Extrapolationcited by 0
  16. 2024Semantically Guided Action Anticipationcited by 0
  17. 2025Masked Language Prompting for Generative Data Augmentation in Few-shot Fashion Style Recognitioncited by 0
  18. 2025TRUST: Leveraging Text Robustness for Unsupervised Domain Adaptationcited by 0
  19. 2025Robust Plant Disease Diagnosis with Few Target-Domain Samplescited by 0
  20. 2025Dynamic Multi-level Weighted Alignment Network for Zero-shot Sketch-based Image Retrievalcited by 0
  21. 2025A Dual-stage Prompt-driven Privacy-preserving Paradigm for Person Re-Identificationcited by 0
  22. 2026Attributes Should Come from Images, Not Class Names: Distribution-Conditioned Attribute Selection for Vision-Language Modelscited by 0