mlsanityData to 14 Oct 2026

Deep Feature Registration for Unsupervised Domain Adaptation

arXiv 2310.16100 ↗First posted 24 Oct 2023cs.CVcited by 0

Not on the map. Why?

Abstract (arXiv)

While unsupervised domain adaptation has been explored to leverage the knowledge from a labeled source domain to an unlabeled target domain, existing methods focus on the distribution alignment between two domains. However, how to better align source and target features is not well addressed. In this paper, we propose a deep feature registration (DFR) model to generate registered features that maintain domain invariant features and simultaneously minimize the domain-dissimilarity of registered features and target features via histogram matching. We further employ a pseudo label refinement process, which considers both probabilistic soft selection and center-based hard selection to improve the quality of pseudo labels in the target domain. Extensive experiments on multiple UDA benchmarks demonstrate the effectiveness of our DFR model, resulting in new state-of-the-art performance.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 31 of its 46 references that are in the map. First posted on arXiv 24 Oct 2023.

Builds on

31 of 46 references.

References · 31

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2015Domain-Adversarial Training of Neural Networkscited by 3,044
  3. 2015Learning Transferable Features with Deep Adaptation Networkscited by 1,329
  4. 2017Adversarial Discriminative Domain Adaptationcited by 1,311
  5. 2016Deep CORAL: Correlation Alignment for Deep Domain Adaptationcited by 1,200
  6. 2017Deep Hashing Network for Unsupervised Domain Adaptationcited by 1,188
  7. 2017CyCADA: Cycle-Consistent Adversarial Domain Adaptationcited by 1,082
  8. 2016Deep Transfer Learning with Joint Adaptation Networkscited by 612
  9. 2014Deep Domain Confusion: Maximizing for Domain Invariancecited by 600
  10. 2017VisDA: The Visual Domain Adaptation Challengecited by 435
  11. 2019Contrastive Adaptation Network for Unsupervised Domain Adaptationcited by 407
  12. 2019Sliced Wasserstein Discrepancy for Unsupervised Domain Adaptationcited by 235
19 more
  1. 2018DeepJDOT: Deep Joint Distribution Optimal Transport for Unsupervised Domain Adaptationcited by 214
  2. 2018Progressive Feature Alignment for Unsupervised Domain Adaptationcited by 183
  3. 2017Asymmetric Tri-training for Unsupervised Domain Adaptationcited by 152
  4. 2020Unsupervised Domain Adaptation via Structurally Regularized Deep Clusteringcited by 140
  5. 2019Domain-Symmetric Networks for Adversarial Domain Adaptationcited by 120
  6. 2018Visual Domain Adaptation with Manifold Embedded Distribution Alignmentcited by 91
  7. 2019Discriminative Adversarial Domain Adaptationcited by 74
  8. 2014Domain Adaptive Neural Networks for Object Recognitioncited by 52
  9. 2017Joint Geometrical and Statistical Alignment for Visual Domain Adaptationcited by 43
  10. 2020Domain Conditioned Adaptation Networkcited by 43
  11. 2020Label Propagation with Augmented Anchors: A Simple Semi-Supervised Learning baseline for Unsupervised Domain Adaptationcited by 35
  12. 2019On Minimum Discrepancy Estimation for Deep Domain Adaptationcited by 34
  13. 2020Unsupervised Domain Adaptation via Discriminative Manifold Propagationcited by 33
  14. 2018Adversarial Teacher-Student Learning for Unsupervised Domain Adaptationcited by 28
  15. 2020Impact of ImageNet Model Selection on Domain Adaptationcited by 15
  16. 2021Deep Spherical Manifold Gaussian Kernel for Unsupervised Domain Adaptationcited by 9
  17. 2021Efficient Pre-trained Features and Recurrent Pseudo-Labeling in Unsupervised Domain Adaptationcited by 4
  18. 2021Enhanced Separable Disentanglement for Unsupervised Domain Adaptationcited by 4
  19. 2021Deep Least Squares Alignment for Unsupervised Domain Adaptationcited by 3

Built on by

Not cited yet.