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

Towards Generalizing to Unseen Domains with Few Labels (2403.11674v3)

Published 18 Mar 2024 in cs.CV

Abstract: We approach the challenge of addressing semi-supervised domain generalization (SSDG). Specifically, our aim is to obtain a model that learns domain-generalizable features by leveraging a limited subset of labelled data alongside a substantially larger pool of unlabeled data. Existing domain generalization (DG) methods which are unable to exploit unlabeled data perform poorly compared to semi-supervised learning (SSL) methods under SSDG setting. Nevertheless, SSL methods have considerable room for performance improvement when compared to fully-supervised DG training. To tackle this underexplored, yet highly practical problem of SSDG, we make the following core contributions. First, we propose a feature-based conformity technique that matches the posterior distributions from the feature space with the pseudo-label from the model's output space. Second, we develop a semantics alignment loss to learn semantically-compatible representations by regularizing the semantic structure in the feature space. Our method is plug-and-play and can be readily integrated with different SSL-based SSDG baselines without introducing any additional parameters. Extensive experimental results across five challenging DG benchmarks with four strong SSL baselines suggest that our method provides consistent and notable gains in two different SSDG settings.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (61)
  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. Invariant risk minimization. arXiv preprint arXiv:1907.02893, 2019.
  3. Learning with pseudo-ensembles. Advances in neural information processing systems, 27, 2014.
  4. Metareg: Towards domain generalization using meta-regularization. In NeurIPS, pages 998–1008, 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. Swad: Domain generalization by seeking flat minima. NeurIPS, 34, 2021.
  10. Learning to balance specificity and invariance for in and out of domain generalization. 2020.
  11. Softmatch: Addressing the quantity-quality tradeoff in semi-supervised learning. In The Eleventh International Conference on Learning Representations, 2023.
  12. Imagenet: A large-scale hierarchical image database. In 2009 IEEE conference on computer vision and pattern recognition, pages 248–255. Ieee, 2009.
  13. An image is worth 16x16 words: Transformers for image recognition at scale. arXiv preprint arXiv:2010.11929, 2020.
  14. Domain generalization via model-agnostic learning of semantic features. In NeurIPS, pages 6450–6461, 2019.
  15. Domain generalization for object recognition with multi-task autoencoders. In ICCV, 2015.
  16. Semi-supervised learning by entropy minimization. Advances in neural information processing systems, 17, 2004.
  17. In search of lost domain generalization. ArXiv, abs/2007.01434, 2021.
  18. Deep residual learning for image recognition. In Proceedings of the IEEE conference on computer vision and pattern recognition, pages 770–778, 2016.
  19. Cycada: Cycle-consistent adversarial domain adaptation. In International conference on machine learning, pages 1989–1998. Pmlr, 2018.
  20. Mode-guided feature augmentation for domain generalization. In Proc. Brit. Mach. Vis. Conf., 2021.
  21. Selfreg: Self-supervised contrastive regularization for domain generalization. In ICCV, pages 9619–9628, 2021.
  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, page 896, 2013.
  23. Deeper, broader and artier domain generalization. In ICCV, pages 5542–5550, 2017.
  24. Episodic training for domain generalization. In ICCV, 2019.
  25. Domain generalization with adversarial feature learning. In CVPR, pages 5400–5409, 2018.
  26. 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.
  27. Unified deep supervised domain adaptation and generalization. In ICCV, pages 5715–5725, 2017.
  28. Domain generalization via invariant feature representation. In ICML, 2013.
  29. Distributionally robust neural networks for group shifts: On the importance of regularization for worst-case generalization. arXiv preprint arXiv:1911.08731, 2019.
  30. Learning to optimize domain specific normalization for domain generalization. 2020.
  31. Generalizing across domains via cross-gradient training. arXiv preprint arXiv:1804.10745, 2018.
  32. Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556, 2014.
  33. Fixmatch: Simplifying semi-supervised learning with consistency and confidence. Advances in neural information processing systems, 33:596–608, 2020.
  34. Dynamic domain generalization. arXiv preprint arXiv:2205.13913, 2022.
  35. Mean teachers are better role models: Weight-averaged consistency targets improve semi-supervised deep learning results. Advances in neural information processing systems, 30, 2017.
  36. Unbiased look at dataset bias. In CVPR 2011, pages 1521–1528. IEEE, 2011.
  37. Vladimir Vapnik. The nature of statistical learning theory. Springer science & business media, 1999.
  38. Deep hashing network for unsupervised domain adaptation. In CVPR, pages 5018–5027, 2017.
  39. Generalizing to unseen domains via adversarial data augmentation. In NeurIPS, 2018.
  40. High frequency component helps explain the generalization of convolutional neural networks. arXiv preprint arXiv:1905.13545, 2019.
  41. Better pseudo-label: Joint domain-aware label and dual-classifier for semi-supervised domain generalization. Pattern Recognition, 133:108987, 2023a.
  42. Learning from extrinsic and intrinsic supervisions for domain generalization. 2020.
  43. Freematch: Self-adaptive thresholding for semi-supervised learning. 2023b.
  44. Unsupervised data augmentation for consistency training. Advances in neural information processing systems, 33:6256–6268, 2020a.
  45. Self-training with noisy student improves imagenet classification. In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, pages 10687–10698, 2020b.
  46. Exploiting low-rank structure from latent domains for domain generalization. In European Conference on Computer Vision, pages 628–643. Springer, 2014.
  47. Improve unsupervised domain adaptation with mixup training. arXiv preprint arXiv:2001.00677, 2020.
  48. A survey on deep semi-supervised learning. IEEE Transactions on Knowledge and Data Engineering, 2022.
  49. 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.
  50. Label-efficient domain generalization via collaborative exploration and generalization. In Proceedings of the 30th ACM International Conference on Multimedia, pages 2361–2370, 2022.
  51. Latent domain generation for unsupervised domain adaptation object counting. IEEE Transactions on Multimedia, 2022.
  52. Flexmatch: Boosting semi-supervised learning with curriculum pseudo labeling. Advances in Neural Information Processing Systems, 34:18408–18419, 2021.
  53. mixup: Beyond empirical risk minimization. arXiv preprint arXiv:1710.09412, 2017.
  54. mixup: Beyond empirical risk minimization. In ICLR (ICLR), 2018.
  55. Domain adaptation under target and conditional shift. In International conference on machine learning, pages 819–827. PMLR, 2013.
  56. Youshan Zhang. A survey of unsupervised domain adaptation for visual recognition. arXiv preprint arXiv:2112.06745, 2021.
  57. Learning with local and global consistency. Advances in neural information processing systems, 16, 2003.
  58. Deep domain-adversarial image generation for domain generalisation. In Proceedings of the AAAI Conference on Artificial Intelligence, pages 13025–13032, 2020a.
  59. Learning to generate novel domains for domain generalization. In European Conference on Computer Vision, pages 561–578. Springer, 2020b.
  60. Domain adaptive ensemble learning. CoRR, abs/2003.07325, 2020c.
  61. Semi-supervised domain generalization with stochastic stylematch. International Journal of Computer Vision, pages 1–11, 2023.
Citations (1)
View on Semantic Scholar

Summary

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

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