mlsanityData to 14 Oct 2026

A3: Active Adversarial Alignment for Source-Free Domain Adaptation

arXiv 2409.18418 ↗First posted 27 Sep 2024cs.LG cs.AI cs.CVcited by 0

Not on the map. Why?

Abstract (arXiv)

Unsupervised domain adaptation (UDA) aims to transfer knowledge from a labeled source domain to an unlabeled target domain. Recent works have focused on source-free UDA, where only target data is available. This is challenging as models rely on noisy pseudo-labels and struggle with distribution shifts. We propose Active Adversarial Alignment (A3), a novel framework combining self-supervised learning, adversarial training, and active learning for robust source-free UDA. A3 actively samples informative and diverse data using an acquisition function for training. It adapts models via adversarial losses and consistency regularization, aligning distributions without source data access. A3 advances source-free UDA through its synergistic integration of active and adversarial learning for effective domain alignment and noise reduction.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 27 of its 45 references that are in the map. First posted on arXiv 27 Sep 2024.

Builds on

27 of 45 references.

References · 27

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2020A Simple Framework for Contrastive Learning of Visual Representationscited by 12,049
  3. 2016Overcoming catastrophic forgetting in neural networkscited by 4,787
  4. 2020Unsupervised Learning of Visual Features by Contrasting Cluster Assignmentscited by 2,857
  5. 2018Moment Matching for Multi-Source Domain Adaptationcited by 1,331
  6. 2017Adversarial Discriminative Domain Adaptationcited by 1,311
  7. 2017Deep Hashing Network for Unsupervised Domain Adaptationcited by 1,188
  8. 2017Virtual Adversarial Training: A Regularization Method for Supervised and Semi-Supervised Learningcited by 920
  9. 2020Do We Really Need to Access the Source Data? Source Hypothesis Transfer for Unsupervised Domain Adaptationcited by 848
  10. 2014Deep Domain Confusion: Maximizing for Domain Invariancecited by 600
  11. 2019BatchBALD: Efficient and Diverse Batch Acquisition for Deep Bayesian Active Learningcited by 432
  12. 2019Confidence Regularized Self-Trainingcited by 419
15 more
  1. 2019Semi-supervised Domain Adaptation via Minimax Entropycited by 335
  2. 2018A DIRT-T Approach to Unsupervised Domain Adaptationcited by 215
  3. 2020FixBi: Bridging Domain Spaces for Unsupervised Domain Adaptationcited by 124
  4. 2020SENTRY: Selective Entropy Optimization via Committee Consistency for Unsupervised Domain Adaptationcited by 78
  5. 2019Active Adversarial Domain Adaptationcited by 73
  6. 2020Active Domain Adaptation via Clustering Uncertainty-weighted Embeddingscited by 72
  7. 2019Bayesian Batch Active Learning as Sparse Subset Approximationcited by 68
  8. 2020Rethinking Distributional Matching Based Domain Adaptationcited by 33
  9. 2021Visualizing Adapted Knowledge in Domain Transfercited by 32
  10. 2022PT4AL: Using Self-Supervised Pretext Tasks for Active Learningcited by 27
  11. 2021Source-free Domain Adaptation via Distributional Alignment by Matching Batch Normalization Statisticscited by 25
  12. 2021S3VAADA: Submodular Subset Selection for Virtual Adversarial Active Domain Adaptationcited by 19
  13. 2022Variational Model Perturbation for Source-Free Domain Adaptationcited by 18
  14. 2023Gradual Source Domain Expansion for Unsupervised Domain Adaptationcited by 12
  15. 2022Local Context-Aware Active Domain Adaptationcited by 4

Built on by

Not cited yet.