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

Improving Pseudo-labelling and Enhancing Robustness for Semi-Supervised Domain Generalization (2401.13965v2)

Published 25 Jan 2024 in cs.CV

Abstract: Beyond attaining domain generalization (DG), visual recognition models should also be data-efficient during learning by leveraging limited labels. We study the problem of Semi-Supervised Domain Generalization (SSDG) which is crucial for real-world applications like automated healthcare. SSDG requires learning a cross-domain generalizable model when the given training data is only partially labelled. Empirical investigations reveal that the DG methods tend to underperform in SSDG settings, likely because they are unable to exploit the unlabelled data. Semi-supervised learning (SSL) shows improved but still inferior results compared to fully-supervised learning. A key challenge, faced by the best-performing SSL-based SSDG methods, is selecting accurate pseudo-labels under multiple domain shifts and reducing overfitting to source domains under limited labels. In this work, we propose new SSDG approach, which utilizes a novel uncertainty-guided pseudo-labelling with model averaging (UPLM). Our uncertainty-guided pseudo-labelling (UPL) uses model uncertainty to improve pseudo-labelling selection, addressing poor model calibration under multi-source unlabelled data. The UPL technique, enhanced by our novel model averaging (MA) strategy, mitigates overfitting to source domains with limited labels. Extensive experiments on key representative DG datasets suggest that our method demonstrates effectiveness against existing methods. Our code and chosen labelled data seeds are available on GitHub: https://github.com/Adnan-Khan7/UPLM

View on arXiv
Definition Search Book Streamline Icon: https://streamlinehq.com
References (45)
  1. Recognition in terra incognita. In Proceedings of the European conference on computer vision (ECCV), pages 456–473.
  2. Improved regularization of convolutional neural networks with cutout. arXiv preprint arXiv:1708.04552.
  3. Domain generalization via model-agnostic learning of semantic features. Advances in Neural Information Processing Systems, 32.
  4. Unbiased metric learning: On the utilization of multiple datasets and web images for softening bias. In Proceedings of the IEEE International Conference on Computer Vision, pages 1657–1664.
  5. Dropout as a bayesian approximation: Representing model uncertainty in deep learning. In international conference on machine learning, pages 1050–1059. PMLR.
  6. Domain generalization for object recognition with multi-task autoencoders. In Proceedings of the IEEE international conference on computer vision, pages 2551–2559.
  7. Semi-supervised learning by entropy minimization. Advances in neural information processing systems, 17.
  8. In search of lost domain generalization. arXiv preprint arXiv:2007.01434.
  9. Deep residual learning for image recognition. In Proceedings of the IEEE conference on computer vision and pattern recognition, pages 770–778.
  10. Deep residual learning for image recognition. In CVPR, pages 770–778.
  11. Simultaneous deep transfer across domains and tasks. Domain Adaptation in Computer Vision Applications, pages 173–187.
  12. Self-challenging improves cross-domain generalization.
  13. Modelling uncertainty in deep learning for camera relocalization. In 2016 IEEE international conference on Robotics and Automation (ICRA), pages 4762–4769. IEEE.
  14. What uncertainties do we need in bayesian deep learning for computer vision? Advances in neural information processing systems, 30.
  15. Contrastive self-supervised learning: a survey on different architectures. In 2022 2nd International Conference on Artificial Intelligence (ICAI), pages 1–6. IEEE.
  16. Object detection in aerial images : A case study on performance improvement. In 2022 International Conference on Artificial Intelligence of Things (ICAIoT), pages 1–9.
  17. Mode-guided feature augmentation for domain generalization. In Proc. Brit. Mach. Vis. Conf.
  18. Selfreg: Self-supervised contrastive regularization for domain generalization. In Proceedings of the IEEE/CVF International Conference on Computer Vision, pages 9619–9628.
  19. Imagenet classification with deep convolutional neural networks. Communications of the ACM, 60(6):84–90.
  20. Simple and scalable predictive uncertainty estimation using deep ensembles. Advances in neural information processing systems, 30.
  21. Deeper, broader and artier domain generalization. In Proceedings of the IEEE international conference on computer vision, pages 5542–5550.
  22. Semi-supervised domain generalization in real world: New benchmark and strong baseline. arXiv preprint arXiv:2111.10221.
  23. Domain generalization via invariant feature representation. In International conference on machine learning, pages 10–18. PMLR.
  24. Nesterov, Y. E. (1983). A method of solving a convex programming problem with convergence rate o\\\backslash\bigl(k^2\\\backslash\bigr). In Doklady Akademii Nauk, volume 269, pages 543–547. Russian Academy of Sciences.
  25. Multimatch: Multi-task learning for semi-supervised domain generalization. arXiv preprint arXiv:2208.05853.
  26. In defense of pseudo-labeling: An uncertainty-aware pseudo-label selection framework for semi-supervised learning. In International Conference on Learning Representations.
  27. A stochastic approximation method. The annals of mathematical statistics, pages 400–407.
  28. Regularization with stochastic transformations and perturbations for deep semi-supervised learning. Advances in neural information processing systems, 29.
  29. Generalizing across domains via cross-gradient training. arXiv preprint arXiv:1804.10745.
  30. Open domain generalization with domain-augmented meta-learning. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 9624–9633.
  31. Understanding measures of uncertainty for adversarial example detection. arXiv preprint arXiv:1803.08533.
  32. Fixmatch: Simplifying semi-supervised learning with consistency and confidence. Advances in neural information processing systems, 33:596–608.
  33. Mean teachers are better role models: Weight-averaged consistency targets improve semi-supervised deep learning results. Advances in neural information processing systems, 30.
  34. Simultaneous deep transfer across domains and tasks. In Proceedings of the IEEE international conference on computer vision, pages 4068–4076.
  35. Vapnik, V. (1999). The nature of statistical learning theory. Springer science & business media.
  36. Deep hashing network for unsupervised domain adaptation. In Proceedings of the IEEE conference on computer vision and pattern recognition, pages 5018–5027.
  37. Generalizing to unseen domains via adversarial data augmentation. Advances in neural information processing systems, 31.
  38. Learning from extrinsic and intrinsic supervisions for domain generalization.
  39. Self-training with noisy student improves imagenet classification. In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, pages 10687–10698.
  40. Multi-view discriminant transfer learning.
  41. Enhancing pseudo label quality for semi-supervised domain-generalized medical image segmentation. In Proceedings of the AAAI Conference on Artificial Intelligence, volume 36, pages 3099–3107.
  42. Label-efficient domain generalization via collaborative exploration and generalization. In Proceedings of the 30th ACM International Conference on Multimedia, pages 2361–2370.
  43. Delving deep into the generalization of vision transformers under distribution shifts. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 7277–7286.
  44. Semi-supervised domain generalization with stochastic stylematch. arXiv preprint arXiv:2106.00592.
  45. Domain generalization with mixstyle. arXiv preprint arXiv:2104.02008.
User Edit Pencil Streamline Icon: https://streamlinehq.com
Authors (3)
  1. Adnan Khan (9 papers)
  2. Mai A. Shaaban (7 papers)
  3. Muhammad Haris Khan (68 papers)
Citations (2)
View on Semantic Scholar

Summary

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

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

GitHub

  1. GitHub - AiMl-hub/UPLM: Uncertainty-Guided Pseudo-Labelling with Model Averaging (10 stars)