mlsanityData to 7 Oct 2026

OT-VP: Optimal Transport-guided Visual Prompting for Test-Time Adaptation

arXiv 2407.09498 ↗First posted 12 Jun 2024cs.CV cs.LGcited by 17

Not on the map. Why?

Abstract (arXiv)

Vision Transformers (ViTs) have demonstrated remarkable capabilities in learning representations, but their performance is compromised when applied to unseen domains. Previous methods either engage in prompt learning during the training phase or modify model parameters at test time through entropy minimization. The former often overlooks unlabeled target data, while the latter doesn't fully address domain shifts. In this work, our approach, Optimal Transport-guided Test-Time Visual Prompting (OT-VP), handles these problems by leveraging prompt learning at test time to align the target and source domains without accessing the training process or altering pre-trained model parameters. This method involves learning a universal visual prompt for the target domain by optimizing the Optimal Transport distance.OT-VP, with only four learned prompt tokens, exceeds state-of-the-art performance across three stylistic datasets-PACS, VLCS, OfficeHome, and one corrupted dataset ImageNet-C. Additionally, OT-VP operates efficiently, both in terms of memory and computation, and is adaptable for extension to online settings.

Key facts. Cited by 17 papers in the map (data through 7 Oct 2026). Builds on 38 of its 57 references that are in the map. First posted on arXiv 12 Jun 2024.

Builds on

38 of 57 references.

References · 38

  1. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,456
  2. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 29,915
  3. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,160
  4. 2021Swin Transformer: Hierarchical Vision Transformer using Shifted Windowscited by 12,082
  5. 2016Overcoming catastrophic forgetting in neural networkscited by 4,718
  6. 2019Benchmarking Neural Network Robustness to Common Corruptions and Perturbationscited by 2,857
  7. 2013Sinkhorn Distances: Lightspeed Computation of Optimal Transportation Distancescited by 2,277
  8. 2022Visual Prompt Tuningcited by 1,674
  9. 2019Do ImageNet Classifiers Generalize to ImageNet?cited by 1,507
  10. 2020WILDS: A Benchmark of in-the-Wild Distribution Shiftscited by 1,366
  11. 2017Deep Hashing Network for Unsupervised Domain Adaptationcited by 1,181
  12. 2020In Search of Lost Domain Generalizationcited by 1,042
26 more
  1. 2017Deeper, Broader and Artier Domain Generalizationcited by 983
  2. 2021Learning to Prompt for Continual Learningcited by 938
  3. 2020Do We Really Need to Access the Source Data? Source Hypothesis Transfer for Unsupervised Domain Adaptationcited by 844
  4. 2018Computational Optimal Transportcited by 765
  5. 2021Domain Generalization: A Surveycited by 760
  6. 2021Do Vision Transformers See Like Convolutional Neural Networks?cited by 671
  7. 2015Optimal Transport for Domain Adaptationcited by 457
  8. 2021Intriguing Properties of Vision Transformerscited by 446
  9. 2020Improving robustness against common corruptions by covariate shift adaptationcited by 427
  10. 2023Towards Stable Test-Time Adaptation in Dynamic Wild Worldcited by 409
  11. 2023A Comprehensive Survey on Test-Time Adaptation under Distribution Shiftscited by 353
  12. 2017Certifying Some Distributional Robustness with Principled Adversarial Trainingcited by 333
  13. 2020Source Data-absent Unsupervised Domain Adaptation through Hypothesis Transfer and Labeling Transfercited by 173
  14. 2020Geometric Dataset Distances via Optimal Transportcited by 157
  15. 2021The Norm Must Go On: Dynamic Unsupervised Domain Adaptation by Normalizationcited by 131
  16. 2022Domain Adaptation via Prompt Learningcited by 128
  17. 2023Align Your Prompts: Test-Time Prompting with Distribution Alignment for Zero-Shot Generalizationcited by 100
  18. 2022Decorate the Newcomers: Visual Domain Prompt for Continual Test Time Adaptationcited by 98
  19. 2022Visual Prompt Tuning for Test-time Domain Adaptationcited by 97
  20. 2024Test-Time Model Adaptation with Only Forward Passescited by 74
  21. 2021Test-Time Adaptation to Distribution Shift by Confidence Maximization and Input Transformationcited by 67
  22. 2021OTCE: A Transferability Metric for Cross-Domain Cross-Task Representationscited by 62
  23. 2022Prompt Vision Transformer for Domain Generalizationcited by 52
  24. 2022ActMAD: Activation Matching to Align Distributions for Test-Time-Trainingcited by 38
  25. 2023Diffusion-TTA: Test-time Adaptation of Discriminative Models via Generative Feedbackcited by 27
  26. 2023On the Fly Neural Style Smoothing for Risk-Averse Domain Generalizationcited by 3

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 2; 2025: 9; 2026: 6.

17 papers.

Sort:

By area:

  1. 2024DPCore: Dynamic Prompt Coreset for Continual Test-Time Adaptationcited by 33
  2. 2025Prompt-based Adaptation in Large-scale Vision Models: A Surveycited by 21
  3. 2025Doctor Approved: Generating Medically Accurate Skin Disease Images through AI-Expert Feedbackcited by 9
  4. 2025Visual Variational Autoencoder Prompt Tuningcited by 8
  5. 2025All You Need is One: Capsule Prompt Tuning with a Single Vectorcited by 8
  6. 2025Revisiting semi-supervised learning in the era of foundation modelscited by 6
  7. 2024Semantic Anchor Transport: Robust Test-Time Adaptation for Vision-Language Modelscited by 3
  8. 2025ZeroSiam: An Efficient Asymmetry for Test-Time Entropy Optimization without Collapsecited by 3
  9. 2025Class-aware Domain Knowledge Fusion and Fission for Continual Test-Time Adaptationcited by 3
  10. 2025PAID: Pairwise Angular-Invariant Decomposition for Continual Test-Time Adaptationcited by 2
  11. 2026Lessons and Open Questions from a Unified Study of Camera-Trap Species Recognition Over Timecited by 2
  12. 2026Adapting in the Dark: Efficient and Stable Test-Time Adaptation for Black-Box Modelscited by 2
5 more
  1. 2026Continual Test-Time Adaptation in Computer Vision: Methods, Benchmarks, and Future Directionscited by 1
  2. 2025Hierarchical Adaptive networks with Task vectors for Test-Time Adaptationcited by 0
  3. 2026Beyond Low-Rank: Low-Rank Sparse Prompting via Spiking Neural Network and Prompt Factorizationcited by 0
  4. 2026Less Tokens, Better Forecasts: Sparse Residual Routing for Efficient Weather Predictioncited by 0
  5. 2026How Medical VLMs Underutilize Their Vision Encoders: A Dermatology Perspectivecited by 0