mlsanityData to 14 Oct 2026

Contrastive Test-Time Adaptation

arXiv 2204.10377 ↗First posted 21 Apr 2022cs.CVcited by 261

Not on the map. Why?

Cited by 22 in Multimodal LLMs / vision-language models, but placed by its own abstract, which didn’t fit.

Abstract (arXiv)

Test-time adaptation is a special setting of unsupervised domain adaptation where a trained model on the source domain has to adapt to the target domain without accessing source data. We propose a novel way to leverage self-supervised contrastive learning to facilitate target feature learning, along with an online pseudo labeling scheme with refinement that significantly denoises pseudo labels. The contrastive learning task is applied jointly with pseudo labeling, contrasting positive and negative pairs constructed similarly as MoCo but with source-initialized encoder, and excluding same-class negative pairs indicated by pseudo labels. Meanwhile, we produce pseudo labels online and refine them via soft voting among their nearest neighbors in the target feature space, enabled by maintaining a memory queue. Our method, AdaContrast, achieves state-of-the-art performance on major benchmarks while having several desirable properties compared to existing works, including memory efficiency, insensitivity to hyper-parameters, and better model calibration. Project page: sites.google.com/view/adacontrast.

Key facts. Cited by 261 papers in the map (data through 14 Oct 2026). Builds on 39 of its 59 references that are in the map. First posted on arXiv 21 Apr 2022.

Builds on

39 of 59 references.

References · 39

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,305
  3. 2020A Simple Framework for Contrastive Learning of Visual Representationscited by 12,049
  4. 2018Representation Learning with Contrastive Predictive Codingcited by 7,777
  5. 2019Momentum Contrast for Unsupervised Visual Representation Learningcited by 7,513
  6. 2015Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shiftcited by 7,005
  7. 2015Rethinking the Inception Architecture for Computer Visioncited by 5,475
  8. 2017On Calibration of Modern Neural Networkscited by 4,960
  9. 2020Bootstrap your own latent: A new approach to self-supervised Learningcited by 4,750
  10. 2015Domain-Adversarial Training of Neural Networkscited by 3,044
  11. 2020Exploring Simple Siamese Representation Learningcited by 2,866
  12. 2020Improved Baselines with Momentum Contrastive Learningcited by 2,287
27 more
  1. 2020FixMatch: Simplifying Semi-Supervised Learning with Consistency and Confidencecited by 2,085
  2. 2014Unsupervised Domain Adaptation by Backpropagationcited by 1,917
  3. 2021Barlow Twins: Self-Supervised Learning via Redundancy Reductioncited by 1,838
  4. 2018Unsupervised Representation Learning by Predicting Image Rotationscited by 1,591
  5. 2016Unsupervised Learning of Visual Representations by Solving Jigsaw Puzzlescited by 1,382
  6. 2020Big Self-Supervised Models are Strong Semi-Supervised Learnerscited by 1,380
  7. 2018Moment Matching for Multi-Source Domain Adaptationcited by 1,331
  8. 2015Learning Transferable Features with Deep Adaptation Networkscited by 1,329
  9. 2017Adversarial Discriminative Domain Adaptationcited by 1,311
  10. 2017CyCADA: Cycle-Consistent Adversarial Domain Adaptationcited by 1,082
  11. 2020Do We Really Need to Access the Source Data? Source Hypothesis Transfer for Unsupervised Domain Adaptationcited by 848
  12. 2014Deep Domain Confusion: Maximizing for Domain Invariancecited by 600
  13. 2018Learning to Adapt Structured Output Space for Semantic Segmentationcited by 584
  14. 2016Weight Normalization: A Simple Reparameterization to Accelerate Training of Deep Neural Networkscited by 543
  15. 2019Self-labelling via simultaneous clustering and representation learningcited by 528
  16. 2018Domain Adaptive Faster R-CNN for Object Detection in the Wildcited by 443
  17. 2017VisDA: The Visual Domain Adaptation Challengecited by 435
  18. 2019Contrastive Adaptation Network for Unsupervised Domain Adaptationcited by 407
  19. 2019Semi-supervised Domain Adaptation via Minimax Entropycited by 335
  20. 2019Sliced Wasserstein Discrepancy for Unsupervised Domain Adaptationcited by 235
  21. 2020Universal Source-Free Domain Adaptationcited by 220
  22. 2017Colorization as a Proxy Task for Visual Understandingcited by 175
  23. 2021Generalized Source-free Domain Adaptationcited by 175
  24. 2020Source Data-absent Unsupervised Domain Adaptation through Hypothesis Transfer and Labeling Transfercited by 173
  25. 2020Universal Domain Adaptation through Self Supervisioncited by 172
  26. 2019Unsupervised Domain Adaptation through Self-Supervisioncited by 116
  27. 2020Domain Adaptation with Auxiliary Target Domain-Oriented Classifiercited by 76

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2022: 18; 2023: 74; 2024: 69; 2025: 57; 2026: 43.

261 papers.

Sort:

By area:

  1. 2023Towards Stable Test-Time Adaptation in Dynamic Wild Worldcited by 415
  2. 2023A Comprehensive Survey on Test-Time Adaptation under Distribution Shiftscited by 359
  3. 2023Robust Test-Time Adaptation in Dynamic Scenarioscited by 189
  4. 2023Diverse Data Augmentation with Diffusions for Effective Test-time Prompt Tuningcited by 154
  5. 2024Efficient Test-Time Adaptation of Vision-Language Modelscited by 141
  6. 2023EcoTTA: Memory-Efficient Continual Test-time Adaptation via Self-distilled Regularizationcited by 123
  7. 2022Robust Mean Teacher for Continual and Gradual Test-Time Adaptationcited by 104
  8. 2023TTN: A Domain-Shift Aware Batch Normalization in Test-Time Adaptationcited by 101
  9. 2022Test-Time Adaptation via Conjugate Pseudo-labelscited by 98
  10. 2022Decorate the Newcomers: Visual Domain Prompt for Continual Test Time Adaptationcited by 98
  11. 2022Visual Prompt Tuning for Test-time Domain Adaptationcited by 97
  12. 2023DELTA: degradation-free fully test-time adaptationcited by 72
38 more
  1. 2023Guiding Pseudo-labels with Uncertainty Estimation for Source-free Unsupervised Domain Adaptationcited by 65
  2. 2023Universal Test-time Adaptation through Weight Ensembling, Diversity Weighting, and Prior Correctioncited by 65
  3. 2023On Pitfalls of Test-Time Adaptationcited by 64
  4. 2023ViDA: Homeostatic Visual Domain Adapter for Continual Test Time Adaptationcited by 58
  5. 2023Source-Free Domain Adaptation with Frozen Multimodal Foundation Modelcited by 55
  6. 2023C-SFDA: A Curriculum Learning Aided Self-Training Framework for Efficient Source Free Domain Adaptationcited by 50
  7. 2023Improved Test-Time Adaptation for Domain Generalizationcited by 47
  8. 2023In Search of Lost Online Test-time Adaptation: A Surveycited by 44
  9. 2023Feature Alignment and Uniformity for Test Time Adaptationcited by 42
  10. 2022PASTA: Proportional Amplitude Spectrum Training Augmentation for Syn-to-Real Domain Generalizationcited by 39
  11. 2023Towards Open-Set Test-Time Adaptation Utilizing the Wisdom of Crowds in Entropy Minimizationcited by 39
  12. 2024Knowledge Composition using Task Vectors with Learned Anisotropic Scalingcited by 37
  13. 2023Continual Test-time Domain Adaptation via Dynamic Sample Selectioncited by 35
  14. 2023On the Robustness of Open-World Test-Time Training: Self-Training with Dynamic Prototype Expansioncited by 34
  15. 2023Towards Real-World Test-Time Adaptation: Tri-Net Self-Training with Balanced Normalizationcited by 34
  16. 2024COME: Test-time adaption by Conservatively Minimizing Entropycited by 31
  17. 2023Continual-MAE: Adaptive Distribution Masked Autoencoders for Continual Test-Time Adaptationcited by 30
  18. 2023Each Test Image Deserves A Specific Prompt: Continual Test-Time Adaptation for 2D Medical Image Segmentationcited by 29
  19. 2023Exploring Sparse Visual Prompt for Domain Adaptive Dense Predictioncited by 28
  20. 2023TeSLA: Test-Time Self-Learning With Automatic Adversarial Augmentationcited by 28
  21. 2024Test-Time Adaptation for Depth Completioncited by 26
  22. 2023TEA: Test-time Energy Adaptationcited by 25
  23. 2024Adapting to Distribution Shift by Visual Domain Prompt Generationcited by 23
  24. 2024Protected Test-Time Adaptation via Online Entropy Matching: A Betting Approachcited by 23
  25. 2024DOTA: Distributional Test-Time Adaptation of Vision-Language Modelscited by 23
  26. 2022CAFA: Class-Aware Feature Alignment for Test-Time Adaptationcited by 21
  27. 2024Proxy Denoising for Source-Free Domain Adaptationcited by 21
  28. 2022Prior Knowledge Guided Unsupervised Domain Adaptationcited by 20
  29. 2023Multi-Modal Continual Test-Time Adaptation for 3D Semantic Segmentationcited by 20
  30. 2023Post-Abstention: Towards Reliably Re-Attempting the Abstained Instances in QAcited by 20
  31. 2024T4P: Test-Time Training of Trajectory Prediction via Masked Autoencoder and Actor-specific Token Memorycited by 20
  32. 2024Test-Time Domain Generalization for Face Anti-Spoofingcited by 20
  33. 2023Revisiting Realistic Test-Time Training: Sequential Inference and Adaptation by Anchored Clustering Regularized Self-Trainingcited by 19
  34. 2024SF(DA)2: Source-free Domain Adaptation Through the Lens of Data Augmentationcited by 19
  35. 2024Unified Entropy Optimization for Open-Set Test-Time Adaptationcited by 19
  36. 2023Efficient Test-Time Adaptation for Super-Resolution with Second-Order Degradation and Reconstructioncited by 18
  37. 2023Persistent Test-time Adaptation in Recurring Testing Scenarioscited by 18
  38. 2023Benchmarking Test-Time Adaptation against Distribution Shifts in Image Classificationcited by 17

50 most cited of 261 All 261 (JSON)