mlsanityData to 7 Oct 2026

Gradual Domain Adaptation via Self-Training of Auxiliary Models

arXiv 2106.09890 ↗First posted 18 Jun 2021cs.LGcited by 8

Not on the map. Why?

Abstract (arXiv)

Domain adaptation becomes more challenging with increasing gaps between source and target domains. Motivated from an empirical analysis on the reliability of labeled source data for the use of distancing target domains, we propose self-training of auxiliary models (AuxSelfTrain) that learns models for intermediate domains and gradually combats the distancing shifts across domains. We introduce evolving intermediate domains as combinations of decreasing proportion of source data and increasing proportion of target data, which are sampled to minimize the domain distance between consecutive domains. Then the source model could be gradually adapted for the use in the target domain by self-training of auxiliary models on evolving intermediate domains. We also introduce an enhanced indicator for sample selection via implicit ensemble and extend the proposed method to semi-supervised domain adaptation. Experiments on benchmark datasets of unsupervised and semi-supervised domain adaptation verify its efficacy.

Key facts. Cited by 8 papers in the map (data through 7 Oct 2026). Builds on 36 of its 57 references that are in the map. First posted on arXiv 18 Jun 2021.

Builds on

36 of 57 references.

References · 36

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,267
  3. 2017mixup: Beyond Empirical Risk Minimizationcited by 5,155
  4. 2016Simple and Scalable Predictive Uncertainty Estimation using Deep Ensemblescited by 3,888
  5. 2015Domain-Adversarial Training of Neural Networkscited by 3,023
  6. 2017Prototypical Networks for Few-shot Learningcited by 3,001
  7. 2019RandAugment: Practical automated data augmentation with a reduced search spacecited by 2,261
  8. 2020FixMatch: Simplifying Semi-Supervised Learning with Consistency and Confidencecited by 2,080
  9. 2014Unsupervised Domain Adaptation by Backpropagationcited by 1,906
  10. 2018Moment Matching for Multi-Source Domain Adaptationcited by 1,327
  11. 2015Learning Transferable Features with Deep Adaptation Networkscited by 1,323
  12. 2019Can You Trust Your Model's Uncertainty? Evaluating Predictive Uncertainty Under Dataset Shiftcited by 1,274
24 more
  1. 2016Deep CORAL: Correlation Alignment for Deep Domain Adaptationcited by 1,194
  2. 2017Deep Hashing Network for Unsupervised Domain Adaptationcited by 1,181
  3. 2019Unsupervised Data Augmentation for Consistency Trainingcited by 1,057
  4. 2014Deep Neural Networks are Easily Fooled: High Confidence Predictions for Unrecognizable Imagescited by 774
  5. 2017Maximum Classifier Discrepancy for Unsupervised Domain Adaptationcited by 682
  6. 2017VisDA: The Visual Domain Adaptation Challengecited by 432
  7. 2019Contrastive Adaptation Network for Unsupervised Domain Adaptationcited by 407
  8. 2019Semi-supervised Domain Adaptation via Minimax Entropycited by 333
  9. 2019Bridging Theory and Algorithm for Domain Adaptationcited by 332
  10. 2020Instance Adaptive Self-Training for Unsupervised Domain Adaptationcited by 177
  11. 2018DLOW: Domain Flow for Adaptation and Generalizationcited by 176
  12. 2020Understanding Self-Training for Gradual Domain Adaptationcited by 149
  13. 2020Unsupervised Domain Adaptation via Structurally Regularized Deep Clusteringcited by 140
  14. 2020Gradually Vanishing Bridge for Adversarial Domain Adaptationcited by 130
  15. 2019Domain-Symmetric Networks for Adversarial Domain Adaptationcited by 120
  16. 2019Self-Training and Adversarial Background Regularization for Unsupervised Domain Adaptive One-Stage Object Detectioncited by 83
  17. 2020Attract, Perturb, and Explore: Learning a Feature Alignment Network for Semi-supervised Domain Adaptationcited by 69
  18. 2020Online Meta-Learning for Multi-Source and Semi-Supervised Domain Adaptationcited by 64
  19. 2018Boosting Domain Adaptation by Discovering Latent Domainscited by 46
  20. 2019On Learning Invariant Representation for Domain Adaptationcited by 38
  21. 2015Transfer Learning from Deep Features for Remote Sensing and Poverty Mappingcited by 37
  22. 2019Blending-target Domain Adaptation by Adversarial Meta-Adaptation Networkscited by 37
  23. 2020Label Propagation with Augmented Anchors: A Simple Semi-Supervised Learning baseline for Unsupervised Domain Adaptationcited by 35
  24. 2020Heuristic Domain Adaptationcited by 19

Built on by

Cited by year

Citing papers per year: 2022: 3; 2023: 2; 2024: 2; 2025: 1.

8 papers.

  1. 2022Introducing Intermediate Domains for Effective Self-Training during Test-Timecited by 12
  2. 2023Gradual Source Domain Expansion for Unsupervised Domain Adaptationcited by 12
  3. 2022Gradual Domain Adaptation via Normalizing Flowscited by 11
  4. 2022Cost-effective Framework for Gradual Domain Adaptation with Multifidelitycited by 3
  5. 2024Gradual Domain Adaptation via Manifold-Constrained Distributionally Robust Optimizationcited by 3
  6. 2023Progressive Classifier and Feature Extractor Adaptation for Unsupervised Domain Adaptation on Point Cloudscited by 2
  7. 2024Bidirectional Multi-Step Domain Generalization for Visible-Infrared Person Re-Identificationcited by 1
  8. 2025GDO:Gradual Domain Osmosiscited by 0