mlsanityData to 7 Oct 2026

On-target Adaptation

arXiv 2109.01087 ↗First posted 2 Sep 2021cs.CV cs.AI cs.LGcited by 15

Not on the map. Why?

Abstract (arXiv)

Domain adaptation seeks to mitigate the shift between training on the source domain and testing on the target domain. Most adaptation methods rely on the source data by joint optimization over source data and target data. Source-free methods replace the source data with a source model by fine-tuning it on target. Either way, the majority of the parameter updates for the model representation and the classifier are derived from the source, and not the target. However, target accuracy is the goal, and so we argue for optimizing as much as possible on the target data. We show significant improvement by on-target adaptation, which learns the representation purely from target data while taking only the source predictions for supervision. In the long-tailed classification setting, we show further improvement by on-target class distribution learning, which learns the (im)balance of classes from target data.

Key facts. Cited by 15 papers in the map (data through 7 Oct 2026). Builds on 57 of its 81 references that are in the map. First posted on arXiv 2 Sep 2021.

Builds on

57 of 81 references.

References · 57

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  3. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,160
  4. 2015Distilling the Knowledge in a Neural Networkcited by 10,076
  5. 2014ImageNet Large Scale Visual Recognition Challengecited by 8,441
  6. 2019Momentum Contrast for Unsupervised Visual Representation Learningcited by 7,482
  7. 2015Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shiftcited by 6,979
  8. 2016SGDR: Stochastic Gradient Descent with Warm Restartscited by 4,993
  9. 2020Bootstrap your own latent: A new approach to self-supervised Learningcited by 4,712
  10. 2015Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classificationcited by 3,590
  11. 2020Exploring Simple Siamese Representation Learningcited by 2,853
  12. 2020Unsupervised Learning of Visual Features by Contrasting Cluster Assignmentscited by 2,845
38 more
  1. 2020Improved Baselines with Momentum Contrastive Learningcited by 2,282
  2. 2020FixMatch: Simplifying Semi-Supervised Learning with Consistency and Confidencecited by 2,080
  3. 2014Unsupervised Domain Adaptation by Backpropagationcited by 1,906
  4. 2021Barlow Twins: Self-Supervised Learning via Redundancy Reductioncited by 1,818
  5. 2019MixMatch: A Holistic Approach to Semi-Supervised Learningcited by 1,390
  6. 2015Learning Transferable Features with Deep Adaptation Networkscited by 1,323
  7. 2017Adversarial Discriminative Domain Adaptationcited by 1,309
  8. 2019Class-Balanced Loss Based on Effective Number of Samplescited by 1,239
  9. 2017Deep Hashing Network for Unsupervised Domain Adaptationcited by 1,181
  10. 2017CyCADA: Cycle-Consistent Adversarial Domain Adaptationcited by 1,079
  11. 2016Temporal Ensembling for Semi-Supervised Learningcited by 1,054
  12. 2019Learning Robust Global Representations by Penalizing Local Predictive Powercited by 1,010
  13. 2019Learning Imbalanced Datasets with Label-Distribution-Aware Margin Losscited by 987
  14. 2019When Does Label Smoothing Help?cited by 985
  15. 2020Do We Really Need to Access the Source Data? Source Hypothesis Transfer for Unsupervised Domain Adaptationcited by 844
  16. 2019Decoupling Representation and Classifier for Long-Tailed Recognitioncited by 806
  17. 2019Large-Scale Long-Tailed Recognition in an Open Worldcited by 704
  18. 2018Learning to Reweight Examples for Robust Deep Learningcited by 670
  19. 2016Deep Transfer Learning with Joint Adaptation Networkscited by 609
  20. 2018Exploring the Limits of Weakly Supervised Pretrainingcited by 604
  21. 2017Unsupervised Image-to-Image Translation Networkscited by 602
  22. 2014Deep Domain Confusion: Maximizing for Domain Invariancecited by 597
  23. 2016Weight Normalization: A Simple Reparameterization to Accelerate Training of Deep Neural Networkscited by 541
  24. 2018Domain Adaptive Faster R-CNN for Object Detection in the Wildcited by 442
  25. 2016Regularization With Stochastic Transformations and Perturbations for Deep Semi-Supervised Learningcited by 441
  26. 2017VisDA: The Visual Domain Adaptation Challengecited by 432
  27. 2020Improving robustness against common corruptions by covariate shift adaptationcited by 427
  28. 2015Return of Frustratingly Easy Domain Adaptationcited by 389
  29. 2019ReMixMatch: Semi-Supervised Learning with Distribution Alignment and Augmentation Anchoringcited by 349
  30. 2016FCNs in the Wild: Pixel-level Adversarial and Constraint-based Adaptationcited by 242
  31. 2014Learning with Pseudo-Ensemblescited by 241
  32. 2019Sliced Wasserstein Discrepancy for Unsupervised Domain Adaptationcited by 235
  33. 2020Universal Source-Free Domain Adaptationcited by 219
  34. 2017Central Moment Discrepancy (CMD) for Domain-Invariant Representation Learningcited by 192
  35. 2021LogME: Practical Assessment of Pre-trained Models for Transfer Learningcited by 168
  36. 2015Cost Sensitive Learning of Deep Feature Representations from Imbalanced Datacited by 167
  37. 2017Learning Discrete Representations via Information Maximizing Self-Augmented Trainingcited by 149
  38. 2017Adversarial Dropout Regularizationcited by 106

50 most cited of 57 All 57 (JSON)

Built on by

Cited by year

Citing papers per year: 2022: 5; 2023: 7; 2024: 3.

15 papers.

Sort:

By area:

  1. 2022Continual Test-Time Domain Adaptationcited by 520
  2. 2023A Comprehensive Survey on Test-Time Adaptation under Distribution Shiftscited by 353
  3. 2022Test-Time Adaptation via Conjugate Pseudo-labelscited by 98
  4. 2022Improving Test-Time Adaptation via Shift-agnostic Weight Regularization and Nearest Source Prototypescited by 67
  5. 2023Guiding Pseudo-labels with Uncertainty Estimation for Source-free Unsupervised Domain Adaptationcited by 63
  6. 2024Beyond Model Adaptation at Test Time: A Surveycited by 55
  7. 2022TeST: Test-time Self-Training under Distribution Shiftcited by 29
  8. 2023TeSLA: Test-Time Self-Learning With Automatic Adversarial Augmentationcited by 28
  9. 2023Revisiting Realistic Test-Time Training: Sequential Inference and Adaptation by Anchored Clustering Regularized Self-Trainingcited by 19
  10. 2023Meta-Personalizing Vision-Language Models to Find Named Instances in Videocited by 16
  11. 2022Test-Time Adaptation for Visual Document Understandingcited by 6
  12. 2023Test-Time Training for Semantic Segmentation with Output Contrastive Losscited by 3
3 more
  1. 2024Time and Frequency Synergy for Source-Free Time-Series Domain Adaptationscited by 1
  2. 2023SelectNAdapt: Support Set Selection for Few-Shot Domain Adaptationcited by 0
  3. 2024Uncertainty-guided Open-Set Source-Free Unsupervised Domain Adaptation with Target-private Class Segregationcited by 0