Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
125 tokens/sec
GPT-4o
47 tokens/sec
Gemini 2.5 Pro Pro
43 tokens/sec
o3 Pro
4 tokens/sec
GPT-4.1 Pro
47 tokens/sec
DeepSeek R1 via Azure Pro
28 tokens/sec
2000 character limit reached

Consistency Regularization for Generalizable Source-free Domain Adaptation (2308.01587v2)

Published 3 Aug 2023 in cs.CV

Abstract: Source-free domain adaptation (SFDA) aims to adapt a well-trained source model to an unlabelled target domain without accessing the source dataset, making it applicable in a variety of real-world scenarios. Existing SFDA methods ONLY assess their adapted models on the target training set, neglecting the data from unseen but identically distributed testing sets. This oversight leads to overfitting issues and constrains the model's generalization ability. In this paper, we propose a consistency regularization framework to develop a more generalizable SFDA method, which simultaneously boosts model performance on both target training and testing datasets. Our method leverages soft pseudo-labels generated from weakly augmented images to supervise strongly augmented images, facilitating the model training process and enhancing the generalization ability of the adapted model. To leverage more potentially useful supervision, we present a sampling-based pseudo-label selection strategy, taking samples with severer domain shift into consideration. Moreover, global-oriented calibration methods are introduced to exploit global class distribution and feature cluster information, further improving the adaptation process. Extensive experiments demonstrate our method achieves state-of-the-art performance on several SFDA benchmarks, and exhibits robustness on unseen testing datasets.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (59)
  1. Mixmatch: A holistic approach to semi-supervised learning. Advances in neural information processing systems, 32, 2019.
  2. Deep clustering for unsupervised learning of visual features. In Proceedings of the European conference on computer vision (ECCV), pages 132–149, 2018.
  3. Lawrence Cayton. Algorithms for manifold learning. Univ. of California at San Diego Tech. Rep, 12(1-17):1, 2005.
  4. Randaugment: Practical automated data augmentation with a reduced search space. In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition workshops, pages 702–703, 2020.
  5. Gradually vanishing bridge for adversarial domain adaptation. In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, pages 12455–12464, 2020.
  6. Unbiased mean teacher for cross-domain object detection. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 4091–4101, 2021.
  7. Bert: Pre-training of deep bidirectional transformers for language understanding. arXiv preprint arXiv:1810.04805, 2018.
  8. Source-free domain adaptation via distribution estimation. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 7212–7222, 2022.
  9. An image is worth 16x16 words: Transformers for image recognition at scale. arXiv preprint arXiv:2010.11929, 2020.
  10. Source-free adaptation to measurement shift via bottom-up feature restoration. In International Conference on Learning Representations, 2021.
  11. Self-ensembling for visual domain adaptation. arXiv preprint arXiv:1706.05208, 2017.
  12. Domain-adversarial training of neural networks. The journal of machine learning research, 17(1):2096–2030, 2016.
  13. A kernel method for the two-sample-problem. Advances in neural information processing systems, 19, 2006.
  14. Spherical space domain adaptation with robust pseudo-label loss. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 9101–9110, 2020.
  15. Hqg-net: Unpaired medical image enhancement with high-quality guidance. arXiv preprint arXiv:2307.07829, 2023.
  16. Camouflaged object detection with feature decomposition and edge reconstruction. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 22046–22055, 2023.
  17. Weakly-supervised concealed object segmentation with sam-based pseudo labeling and multi-scale feature grouping. arXiv preprint arXiv:2305.11003, 2023.
  18. Deep residual learning for image recognition. In Proceedings of the IEEE conference on computer vision and pattern recognition, pages 770–778, 2016.
  19. Rda: Robust domain adaptation via fourier adversarial attacking. In Proceedings of the IEEE/CVF International Conference on Computer Vision, pages 8988–8999, 2021.
  20. Minimum class confusion for versatile domain adaptation. In European Conference on Computer Vision, pages 464–480. Springer, 2020.
  21. Temporal ensembling for semi-supervised learning. arXiv preprint arXiv:1610.02242, 2016.
  22. Dong-Hyun Lee et al. Pseudo-label: The simple and efficient semi-supervised learning method for deep neural networks. In Workshop on challenges in representation learning, ICML, volume 3, page 896, 2013.
  23. Ecacl: A holistic framework for semi-supervised domain adaptation. In Proceedings of the IEEE/CVF International Conference on Computer Vision, pages 8578–8587, 2021.
  24. Source-free video domain adaptation with spatial-temporal-historical consistency learning. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 14643–14652, 2023.
  25. Adversarial feature hallucination networks for few-shot learning. In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, pages 13470–13479, 2020.
  26. Transferable semantic augmentation for domain adaptation. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 11516–11525, 2021.
  27. Do we really need to access the source data? source hypothesis transfer for unsupervised domain adaptation. In International Conference on Machine Learning, pages 6028–6039. PMLR, 2020.
  28. Learning transferable features with deep adaptation networks. In International conference on machine learning, pages 97–105. PMLR, 2015.
  29. Conditional adversarial domain adaptation. NeurIPS, 2018.
  30. Stochastic classifiers for unsupervised domain adaptation. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 9111–9120, 2020.
  31. Virtual adversarial training: a regularization method for supervised and semi-supervised learning. IEEE transactions on pattern analysis and machine intelligence, 41(8):1979–1993, 2018.
  32. Fixbi: Bridging domain spaces for unsupervised domain adaptation. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 1094–1103, 2021.
  33. Moment matching for multi-source domain adaptation. In Proceedings of the IEEE/CVF international conference on computer vision, pages 1406–1415, 2019.
  34. Visda: The visual domain adaptation challenge. arXiv preprint arXiv:1710.06924, 2017.
  35. Beyond sharing weights for deep domain adaptation. IEEE transactions on pattern analysis and machine intelligence, 41(4):801–814, 2018.
  36. Adapting visual category models to new domains. In European conference on computer vision, pages 213–226. Springer, 2010.
  37. Semi-supervised domain adaptation via minimax entropy. In Proceedings of the IEEE/CVF international conference on computer vision, pages 8050–8058, 2019.
  38. Weight normalization: A simple reparameterization to accelerate training of deep neural networks. Advances in neural information processing systems, 29, 2016.
  39. Fixmatch: Simplifying semi-supervised learning with consistency and confidence. Advances in neural information processing systems, 33:596–608, 2020.
  40. Unsupervised domain adaptation via structurally regularized deep clustering. In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, pages 8725–8735, 2020.
  41. Source-free domain adaptive fundus image segmentation with class-balanced mean teacher. arXiv preprint arXiv:2307.09973, 2023.
  42. Mean teachers are better role models: Weight-averaged consistency targets improve semi-supervised deep learning results. Advances in neural information processing systems, 30, 2017.
  43. Deep hashing network for unsupervised domain adaptation. In Proceedings of the IEEE conference on computer vision and pattern recognition, pages 5018–5027, 2017.
  44. Exploring domain-invariant parameters for source free domain adaptation. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 7151–7160, 2022.
  45. Deep visual domain adaptation: A survey. Neurocomputing, 312:135–153, 2018.
  46. Adaptive adversarial network for source-free domain adaptation. In Proceedings of the IEEE/CVF International Conference on Computer Vision, pages 9010–9019, 2021.
  47. Unsupervised data augmentation for consistency training. Advances in Neural Information Processing Systems, 33:6256–6268, 2020.
  48. Self-training with noisy student improves imagenet classification. In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, pages 10687–10698, 2020.
  49. Reliable weighted optimal transport for unsupervised domain adaptation. In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, pages 4394–4403, 2020.
  50. Cdtrans: Cross-domain transformer for unsupervised domain adaptation. arXiv preprint arXiv:2109.06165, 2021.
  51. Exploiting the intrinsic neighborhood structure for source-free domain adaptation. Advances in Neural Information Processing Systems, 34:29393–29405, 2021.
  52. Casting a bait for offline and online source-free domain adaptation. arXiv preprint arXiv:2010.12427, 2020.
  53. Generalized source-free domain adaptation. In Proceedings of the IEEE/CVF International Conference on Computer Vision, pages 8978–8987, 2021.
  54. A survey on deep semi-supervised learning. arXiv preprint arXiv:2103.00550, 2021.
  55. S4l: Self-supervised semi-supervised learning. In Proceedings of the IEEE/CVF International Conference on Computer Vision, pages 1476–1485, 2019.
  56. Flexmatch: Boosting semi-supervised learning with curriculum pseudo labeling. Advances in Neural Information Processing Systems, 34:18408–18419, 2021.
  57. Prototypical pseudo label denoising and target structure learning for domain adaptive semantic segmentation. In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, pages 12414–12424, 2021.
  58. Divide and contrast: Source-free domain adaptation via adaptive contrastive learning. In Conference on Neural Information Processing Systems (NeurIPS), 2022.
  59. Unsupervised domain adaptation for semantic segmentation via class-balanced self-training. In Proceedings of the European conference on computer vision (ECCV), pages 289–305, 2018.
Citations (13)
View on Semantic Scholar

Summary

We haven't generated a summary for this paper yet.

Ai Sparkles Streamline Icon: https://streamlinehq.com Summarize Now