Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
125 tokens/sec
GPT-4o
53 tokens/sec
Gemini 2.5 Pro Pro
42 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

Learnable Data Augmentation for One-Shot Unsupervised Domain Adaptation (2310.02201v1)

Published 3 Oct 2023 in cs.CV

Abstract: This paper presents a classification framework based on learnable data augmentation to tackle the One-Shot Unsupervised Domain Adaptation (OS-UDA) problem. OS-UDA is the most challenging setting in Domain Adaptation, as only one single unlabeled target sample is assumed to be available for model adaptation. Driven by such single sample, our method LearnAug-UDA learns how to augment source data, making it perceptually similar to the target. As a result, a classifier trained on such augmented data will generalize well for the target domain. To achieve this, we designed an encoder-decoder architecture that exploits a perceptual loss and style transfer strategies to augment the source data. Our method achieves state-of-the-art performance on two well-known Domain Adaptation benchmarks, DomainNet and VisDA. The project code is available at https://github.com/IIT-PAVIS/LearnAug-UDA

Definition Search Book Streamline Icon: https://streamlinehq.com
References (24)
  1. Domain separation networks. Advances in neural information processing systems, 29, 2016.
  2. Domain generalization by solving jigsaw puzzles. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), June 2019.
  3. Target-driven one-shot unsupervised domain adaptation. In International Conference on Image Analysis and Processing, pages 87–99. Springer, 2023.
  4. A learned representation for artistic style. arXiv preprint arXiv:1610.07629, 2016.
  5. A neural algorithm of artistic style. arXiv preprint arXiv:1508.06576, 2015.
  6. Image style transfer using convolutional neural networks. In Proceedings of the IEEE conference on computer vision and pattern recognition, pages 2414–2423, 2016.
  7. Arbitrary style transfer in real-time with adaptive instance normalization. In Proceedings of the IEEE international conference on computer vision, pages 1501–1510, 2017.
  8. Perceptual losses for real-time style transfer and super-resolution. In Computer Vision–ECCV 2016: 14th European Conference, Amsterdam, The Netherlands, October 11-14, 2016, Proceedings, Part II 14, pages 694–711. Springer, 2016.
  9. Domain generalization with adversarial feature learning. In Proceedings of the IEEE conference on computer vision and pattern recognition, pages 5400–5409, 2018.
  10. Microsoft coco: Common objects in context. In Computer Vision–ECCV 2014: 13th European Conference, Zurich, Switzerland, September 6-12, 2014, Proceedings, Part V 13, pages 740–755. Springer, 2014.
  11. Adaattn: Revisit attention mechanism in arbitrary neural style transfer. In Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV), pages 6649–6658, October 2021.
  12. Adversarial style mining for one-shot unsupervised domain adaptation. Advances in neural information processing systems, 33:20612–20623, 2020.
  13. Domain generalization via invariant feature representation. In International conference on machine learning, pages 10–18. PMLR, 2013.
  14. Visda: The visual domain adaptation challenge. arXiv preprint arXiv:1710.06924, 2017.
  15. Moment matching for multi-source domain adaptation. In Proceedings of the IEEE/CVF international conference on computer vision, pages 1406–1415, 2019.
  16. Youtube-boundingboxes: A large high-precision human-annotated data set for object detection in video. In proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pages 5296–5305, 2017.
  17. Semi-supervised domain adaptation via minimax entropy. In Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV), October 2019.
  18. Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556, 2014.
  19. Teppei Suzuki. Teachaugment: Data augmentation optimization using teacher knowledge. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pages 10904–10914, June 2022.
  20. Few-shot unsupervised domain adaptation via meta learning. In 2022 IEEE International Conference on Multimedia and Expo (ICME), pages 1–6. IEEE, 2022.
  21. Prototypical cross-domain self-supervised learning for few-shot unsupervised domain adaptation. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 13834–13844, 2021.
  22. Multi-style generative network for real-time transfer. In Proceedings of the European Conference on Computer Vision (ECCV) Workshops, September 2018.
  23. mixup: Beyond empirical risk minimization. arXiv preprint arXiv:1710.09412, 2017.
  24. Separating style and content for generalized style transfer. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), June 2018.
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