Papers
Topics
Authors
Recent
Search
2000 character limit reached

Domain-Guided Weight Modulation for Semi-Supervised Domain Generalization

Published 4 Sep 2024 in cs.CV | (2409.03509v1)

Abstract: Unarguably, deep learning models capable of generalizing to unseen domain data while leveraging a few labels are of great practical significance due to low developmental costs. In search of this endeavor, we study the challenging problem of semi-supervised domain generalization (SSDG), where the goal is to learn a domain-generalizable model while using only a small fraction of labeled data and a relatively large fraction of unlabeled data. Domain generalization (DG) methods show subpar performance under the SSDG setting, whereas semi-supervised learning (SSL) methods demonstrate relatively better performance, however, they are considerably poor compared to the fully-supervised DG methods. Towards handling this new, but challenging problem of SSDG, we propose a novel method that can facilitate the generation of accurate pseudo-labels under various domain shifts. This is accomplished by retaining the domain-level specialism in the classifier during training corresponding to each source domain. Specifically, we first create domain-level information vectors on the fly which are then utilized to learn a domain-aware mask for modulating the classifier's weights. We provide a mathematical interpretation for the effect of this modulation procedure on both pseudo-labeling and model training. Our method is plug-and-play and can be readily applied to different SSL baselines for SSDG. Extensive experiments on six challenging datasets in two different SSDG settings show that our method provides visible gains over the various strong SSL-based SSDG baselines.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (63)
  1. Adaptive consistency regularization for semi-supervised transfer learning. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 6923–6932, 2021.
  2. Abien Fred Agarap. Deep learning using rectified linear units (relu). ArXiv, abs/1803.08375, 2018.
  3. Learning with pseudo-ensembles. In Z. Ghahramani, M. Welling, C. Cortes, N. Lawrence, and K.Q. Weinberger, editors, Advances in Neural Information Processing Systems, volume 27. Curran Associates, Inc., 2014.
  4. Metareg: Towards domain generalization using meta-regularization. Advances in neural information processing systems, 31, 2018.
  5. Recognition in terra incognita. In European Conference on Computer Vision, pages 456–473, 2018.
  6. Mixmatch: A holistic approach to semi-supervised learning. Advances in neural information processing systems, 32, 2019.
  7. Generalizing from several related classification tasks to a new unlabeled sample. NeurIPS, 24:2178–2186, 2011.
  8. Domain generalization by solving jigsaw puzzles. In CVPR, pages 2229–2238, 2019.
  9. Softmatch: Addressing the quantity-quality tradeoff in semi-supervised learning. In The Eleventh International Conference on Learning Representations, 2023.
  10. Imagenet: A large-scale hierarchical image database. In 2009 IEEE conference on computer vision and pattern recognition, pages 248–255. Ieee, 2009.
  11. An image is worth 16x16 words: Transformers for image recognition at scale. arXiv preprint arXiv:2010.11929, 2020.
  12. Domain generalization via model-agnostic learning of semantic features. Advances in neural information processing systems, 32, 2019.
  13. A learned representation for artistic style. In International Conference on Learning Representations, 2017.
  14. Unbiased metric learning: On the utilization of multiple datasets and web images for softening bias. In ICCV, pages 1657–1664, 2013.
  15. Dropout as a bayesian approximation: Representing model uncertainty in deep learning. In Proceedings of the 33rd International Conference on International Conference on Machine Learning - Volume 48, ICML’16, page 1050–1059. JMLR.org, 2016.
  16. Towards generalizing to unseen domains with few labels. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 23691–23700, 2024.
  17. Semi-supervised learning by entropy minimization. Advances in neural information processing systems, 17, 2004.
  18. In search of lost domain generalization. ArXiv, abs/2007.01434, 2021.
  19. Deep residual learning for image recognition. In Proceedings of the IEEE conference on computer vision and pattern recognition, pages 770–778, 2016.
  20. Cycada: Cycle-consistent adversarial domain adaptation. In International conference on machine learning, pages 1989–1998. Pmlr, 2018.
  21. Arbitrary style transfer in real-time with adaptive instance normalization. 2017 IEEE International Conference on Computer Vision (ICCV), pages 1510–1519, 2017.
  22. Mode-guided feature augmentation for domain generalization. In Proc. Brit. Mach. Vis. Conf., 2021.
  23. Temporal ensembling for semi-supervised learning. In International Conference on Learning Representations, 2017.
  24. 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.
  25. Deeper, broader and artier domain generalization. In ICCV, pages 5542–5550, 2017.
  26. Episodic training for domain generalization. In ICCV, 2019.
  27. Domain generalization with adversarial feature learning. In Proceedings of the IEEE conference on computer vision and pattern recognition, pages 5400–5409, 2018.
  28. Deep domain generalization via conditional invariant adversarial networks. In Proceedings of the European conference on computer vision (ECCV), pages 624–639, 2018.
  29. 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.
  30. Domain generalization via invariant feature representation. In ICML, 2013.
  31. Semi-supervised semantic segmentation with cross-consistency training. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 12674–12684, 2020.
  32. Moment matching for multi-source domain adaptation. In ICCV, pages 1406–1415, 2019.
  33. Multimatch: Multi-task learning for semi-supervised domain generalization. ACM Trans. Multimedia Comput. Commun. Appl., 20(6), mar 2024.
  34. Do imagenet classifiers generalize to imagenet? In International conference on machine learning, pages 5389–5400. PMLR, 2019.
  35. Distributionally robust neural networks for group shifts: On the importance of regularization for worst-case generalization. arXiv preprint arXiv:1911.08731, 2019.
  36. Regularization with stochastic transformations and perturbations for deep semi-supervised learning. In Proceedings of the 30th International Conference on Neural Information Processing Systems, NIPS’16, page 1171–1179, Red Hook, NY, USA, 2016. Curran Associates Inc.
  37. Open domain generalization with domain-augmented meta-learning. In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, pages 9624–9633, 2021.
  38. Fixmatch: Simplifying semi-supervised learning with consistency and confidence. Advances in neural information processing systems, 33:596–608, 2020.
  39. Self-distilled vision transformer for domain generalization. In ACCV, pages 3068–3085, 2022.
  40. Mean teachers are better role models: Weight-averaged consistency targets improve semi-supervised deep learning results. Advances in neural information processing systems, 30, 2017.
  41. Deep domain confusion: Maximizing for domain invariance. arXiv preprint arXiv:1412.3474, 2014.
  42. Vladimir Vapnik. The nature of statistical learning theory. Springer science & business media, 1999.
  43. Deep hashing network for unsupervised domain adaptation. In CVPR, pages 5018–5027, 2017.
  44. Generalizing to unseen domains via adversarial data augmentation. In NeurIPS, 2018.
  45. Augmax: Adversarial composition of random augmentations for robust training. Advances in neural information processing systems, 34:237–250, 2021.
  46. Better pseudo-label: Joint domain-aware label and dual-classifier for semi-supervised domain generalization. Pattern Recognition, 133:108987, 2023.
  47. Learning from extrinsic and intrinsic supervisions for domain generalization. 2020.
  48. Freematch: Self-adaptive thresholding for semi-supervised learning. 2023.
  49. Unsupervised data augmentation for consistency training. Advances in neural information processing systems, 33:6256–6268, 2020.
  50. 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.
  51. A fourier-based framework for domain generalization. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 14383–14392, 2021.
  52. Semi-supervised domain generalization with graph-based classifier. In ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pages 1–5, 2023.
  53. Label-efficient domain generalization via collaborative exploration and generalization. In Proceedings of the 30th ACM International Conference on Multimedia, pages 2361–2370, 2022.
  54. Label-efficient domain generalization via collaborative exploration and generalization. In Proceedings of the 30th ACM International Conference on Multimedia, MM ’22, page 2361–2370, New York, NY, USA, 2022. Association for Computing Machinery.
  55. Flexmatch: Boosting semi-supervised learning with curriculum pseudo labeling. Advances in Neural Information Processing Systems, 34:18408–18419, 2021.
  56. mixup: Beyond empirical risk minimization. In ICLR (ICLR), 2018.
  57. Semi-supervised domain generalization with known and unknown classes. In Thirty-seventh Conference on Neural Information Processing Systems, 2023.
  58. Domain generalization via entropy regularization. Advances in Neural Information Processing Systems, 33:16096–16107, 2020.
  59. Adversarial style augmentation for domain generalized urban-scene segmentation. Advances in Neural Information Processing Systems, 35:338–350, 2022.
  60. Domain generalization: A survey. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2022.
  61. Semi-supervised domain generalization with stochastic stylematch. International Journal of Computer Vision, pages 1–11, 2023.
  62. Deep domain-adversarial image generation for domain generalisation. In Proceedings of the AAAI Conference on Artificial Intelligence, volume 34, pages 13025–13032, 2020.
  63. Learning to generate novel domains for domain generalization. In European Conference on Computer Vision, pages 561–578. Springer, 2020.

Summary

No one has generated a summary of this paper yet.

Sign Up to Summarize

Paper to Video (Beta)

No one has generated a video about this paper yet.

Sign Up to Generate All Videos Subscribe on YouTube

Whiteboard

No one has generated a whiteboard explanation for this paper yet.

Sign Up to Generate

Open Problems

We haven't generated a list of open problems mentioned in this paper yet.

Generate Now

Continue Learning

We haven't generated follow-up questions for this paper yet.

Generate Now

Collections

Sign up for free to add this paper to one or more collections.

Sign Up

Tweets

Sign up for free to view the 1 tweet with 0 likes about this paper.

Sign Up for Free