mlsanityData to 14 Oct 2026

Minimal-Entropy Correlation Alignment for Unsupervised Deep Domain Adaptation

arXiv 1711.10288 ↗First posted 28 Nov 2017cs.CVcited by 71

Not on the map. Why?

Abstract (arXiv)

In this work, we face the problem of unsupervised domain adaptation with a novel deep learning approach which leverages on our finding that entropy minimization is induced by the optimal alignment of second order statistics between source and target domains. We formally demonstrate this hypothesis and, aiming at achieving an optimal alignment in practical cases, we adopt a more principled strategy which, differently from the current Euclidean approaches, deploys alignment along geodesics. Our pipeline can be implemented by adding to the standard classification loss (on the labeled source domain), a source-to-target regularizer that is weighted in an unsupervised and data-driven fashion. We provide extensive experiments to assess the superiority of our framework on standard domain and modality adaptation benchmarks.

Key facts. Cited by 71 papers in the map (data through 14 Oct 2026). First posted on arXiv 28 Nov 2017.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 14; 2022: 14; 2023: 18; 2024: 12; 2025: 7; 2026: 6.

71 papers.

Sort:

By area:

  1. 2022Deep Unsupervised Domain Adaptation: A Review of Recent Advances and Perspectivescited by 98
  2. 2021SPG: Unsupervised Domain Adaptation for 3D Object Detection via Semantic Point Generationcited by 94
  3. 2021A Prototype-Oriented Framework for Unsupervised Domain Adaptationcited by 62
  4. 2022CrossMoDA 2021 challenge: Benchmark of Cross-Modality Domain Adaptation techniques for Vestibular Schwannoma and Cochlea Segmentationcited by 58
  5. 2022Semi-Supervised and Unsupervised Deep Visual Learning: A Surveycited by 52
  6. 2021A Survey on Deep Domain Adaptation for LiDAR Perceptioncited by 47
  7. 2022Uncertainty-guided Source-free Domain Adaptationcited by 46
  8. 2021Source-Free Domain Adaptation for Image Segmentationcited by 45
  9. 2021Tune it the Right Way: Unsupervised Validation of Domain Adaptation via Soft Neighborhood Densitycited by 44
  10. 2021Cross-modal Learning for Domain Adaptation in 3D Semantic Segmentationcited by 40
  11. 2021Curriculum Graph Co-Teaching for Multi-Target Domain Adaptationcited by 37
  12. 2022Generative Domain Adaptation for Face Anti-Spoofingcited by 33
38 more
  1. 2023POUF: Prompt-oriented unsupervised fine-tuning for large pre-trained modelscited by 29
  2. 2021UMAD: Universal Model Adaptation under Domain and Category Shiftcited by 23
  3. 2024Protected Test-Time Adaptation via Online Entropy Matching: A Betting Approachcited by 23
  4. 2021Instance Level Affinity-Based Transfer for Unsupervised Domain Adaptationcited by 21
  5. 2022PCGen: Point Cloud Generator for LiDAR Simulationcited by 20
  6. 2023Compositional Semantic Mix for Domain Adaptation in Point Cloud Segmentationcited by 20
  7. 2023Learning to Adapt SAM for Segmenting Cross-domain Point Cloudscited by 20
  8. 2021Unsupervised Domain Adaptation for LiDAR Panoptic Segmentationcited by 19
  9. 2023MoPA: Multi-Modal Prior Aided Domain Adaptation for 3D Semantic Segmentationcited by 17
  10. 2021Unsupervised Noise Adaptive Speech Enhancement by Discriminator-Constrained Optimal Transportcited by 16
  11. 2023Exploiting the Complementarity of 2D and 3D Networks to Address Domain-Shift in 3D Semantic Segmentationcited by 14
  12. 2023Can We Evaluate Domain Adaptation Models Without Target-Domain Labels?cited by 14
  13. 2023LiDAR-UDA: Self-ensembling Through Time for Unsupervised LiDAR Domain Adaptationcited by 14
  14. 2021Secure Domain Adaptation with Multiple Sourcescited by 12
  15. 2021Inferring Latent Domains for Unsupervised Deep Domain Adaptationcited by 11
  16. 2023Test-Time Adaptation Induces Stronger Accuracy and Agreement-on-the-Linecited by 11
  17. 2023Mx2M: Masked Cross-Modality Modeling in Domain Adaptation for 3D Semantic Segmentationcited by 10
  18. 2023Unsupervised Noise adaptation using Data Simulationcited by 9
  19. 2023Better Practices for Domain Adaptationcited by 9
  20. 2022Normalization Perturbation: A Simple Domain Generalization Method for Real-World Domain Shiftscited by 8
  21. 2023Domain Generalization with Adversarial Intensity Attack for Medical Image Segmentationcited by 8
  22. 2022Unsupervised Domain Adaptation for Point Cloud Semantic Segmentation via Graph Matchingcited by 7
  23. 2024DiffuBox: Refining 3D Object Detection with Point Diffusioncited by 7
  24. 2021Colorectal Polyp Classification from White-light Colonoscopy Images via Domain Alignmentcited by 6
  25. 2024UDA-Bench: Revisiting Common Assumptions in Unsupervised Domain Adaptation Using a Standardized Frameworkcited by 6
  26. 2024De-Confusing Pseudo-Labels in Source-Free Domain Adaptationcited by 5
  27. 2022360-MLC: Multi-view Layout Consistency for Self-training and Hyper-parameter Tuningcited by 4
  28. 2024Fusion-then-Distillation: Toward Cross-modal Positive Distillation for Domain Adaptive 3D Semantic Segmentationcited by 4
  29. 2022Heterogeneous Domain Adaptation with Adversarial Neural Representation Learning: Experiments on E-Commerce and Cybersecuritycited by 3
  30. 2025ZeroSiam: An Efficient Asymmetry for Test-Time Entropy Optimization without Collapsecited by 3
  31. 2022Reconciling a Centroid-Hypothesis Conflict in Source-Free Domain Adaptationcited by 2
  32. 2023A Prototype-Oriented Clustering for Domain Shift with Source Privacycited by 2
  33. 2024Exploring Human-in-the-Loop Test-Time Adaptation by Synergizing Active Learning and Model Selectioncited by 2
  34. 2024SKADA-Bench: Benchmarking Unsupervised Domain Adaptation Methods with Realistic Validation On Diverse Modalitiescited by 2
  35. 2024Improving self-training under distribution shifts via anchored confidence with theoretical guaranteescited by 2
  36. 2025Geometric Moment Alignment for Domain Adaptation via Siegel Embeddingscited by 2
  37. 2025Improving Multimodal Distillation for 3D Semantic Segmentation under Domain Shiftcited by 2
  38. 2023A Study of Unsupervised Evaluation Metrics for Practical and Automatic Domain Adaptationcited by 1

50 most cited of 71 All 71 (JSON)