Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
162 tokens/sec
GPT-4o
7 tokens/sec
Gemini 2.5 Pro Pro
45 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

Aggregation of Disentanglement: Reconsidering Domain Variations in Domain Generalization (2302.02350v5)

Published 5 Feb 2023 in cs.CV

Abstract: Domain Generalization (DG) is a fundamental challenge for machine learning models, which aims to improve model generalization on various domains. Previous methods focus on generating domain invariant features from various source domains. However, we argue that the domain variantions also contain useful information, ie, classification-aware information, for downstream tasks, which has been largely ignored. Different from learning domain invariant features from source domains, we decouple the input images into Domain Expert Features and noise. The proposed domain expert features lie in a learned latent space where the images in each domain can be classified independently, enabling the implicit use of classification-aware domain variations. Based on the analysis, we proposed a novel paradigm called Domain Disentanglement Network (DDN) to disentangle the domain expert features from the source domain images and aggregate the source domain expert features for representing the target test domain. We also propound a new contrastive learning method to guide the domain expert features to form a more balanced and separable feature space. Experiments on the widely-used benchmarks of PACS, VLCS, OfficeHome, DomainNet, and TerraIncognita demonstrate the competitive performance of our method compared to the recently proposed alternatives.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (64)
  1. Invariant risk minimization. arXiv preprint arXiv:1907.02893, 2019.
  2. Wasserstein generative adversarial networks. In International conference on machine learning, pages 214–223. PMLR, 2017.
  3. Recognition in terra incognita. In Proceedings of the European conference on computer vision (ECCV), pages 456–473, 2018.
  4. A theory of learning from different domains. Machine learning, 79(1):151–175, 2010.
  5. Domain generalization by marginal transfer learning. The Journal of Machine Learning Research, 22(1):46–100, 2021.
  6. Exploiting domain-specific features to enhance domain generalization. Advances in Neural Information Processing Systems, 34:21189–21201, 2021.
  7. Swad: Domain generalization by seeking flat minima. Advances in Neural Information Processing Systems, 34:22405–22418, 2021.
  8. A simple framework for contrastive learning of visual representations. In International conference on machine learning, pages 1597–1607. PMLR, 2020.
  9. Exploring simple siamese representation learning. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 15750–15758, 2021.
  10. Adaptive methods for real-world domain generalization. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 14340–14349, 2021.
  11. Domain-adversarial training of neural networks. The journal of machine learning research, 17(1):2096–2030, 2016.
  12. Loss function learning for domain generalization by implicit gradient. In International Conference on Machine Learning, pages 7002–7016. PMLR, 2022.
  13. Bootstrap your own latent-a new approach to self-supervised learning. Advances in neural information processing systems, 33:21271–21284, 2020.
  14. In search of lost domain generalization. arXiv preprint arXiv:2007.01434, 2020.
  15. Momentum contrast for unsupervised visual representation learning. In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, pages 9729–9738, 2020.
  16. Domain generalization via multidomain discriminant analysis. In Uncertainty in Artificial Intelligence, pages 292–302. PMLR, 2020.
  17. Fsdr: Frequency space domain randomization for domain generalization. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 6891–6902, 2021.
  18. Self-challenging improves cross-domain generalization. In European Conference on Computer Vision, pages 124–140. Springer, 2020.
  19. Single-side domain generalization for face anti-spoofing. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 8484–8493, 2020.
  20. Selfreg: Self-supervised contrastive regularization for domain generalization. In Proceedings of the IEEE/CVF International Conference on Computer Vision, pages 9619–9628, 2021.
  21. Proxy anchor loss for deep metric learning. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 3238–3247, 2020.
  22. Out-of-distribution generalization via risk extrapolation (rex). In International Conference on Machine Learning, pages 5815–5826. PMLR, 2021.
  23. Learning to generalize: Meta-learning for domain generalization. In Proceedings of the AAAI conference on artificial intelligence, volume 32, 2018.
  24. Deeper, broader and artier domain generalization. In Proceedings of the IEEE international conference on computer vision, pages 5542–5550, 2017.
  25. Domain generalization with adversarial feature learning. In Proceedings of the IEEE conference on computer vision and pattern recognition, pages 5400–5409, 2018.
  26. Progressive domain expansion network for single domain generalization. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 224–233, 2021.
  27. Deep domain generalization via conditional invariant adversarial networks. In Proceedings of the European Conference on Computer Vision (ECCV), pages 624–639, 2018.
  28. Best sources forward: domain generalization through source-specific nets. In 2018 25th IEEE international conference on image processing (ICIP), pages 1353–1357. IEEE, 2018.
  29. Unified deep supervised domain adaptation and generalization. In Proceedings of the IEEE international conference on computer vision, pages 5715–5725, 2017.
  30. Domain generalization via invariant feature representation. In International Conference on Machine Learning, pages 10–18. PMLR, 2013.
  31. Reducing domain gap by reducing style bias. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 8690–8699, 2021.
  32. Representation learning with contrastive predictive coding. arXiv preprint arXiv:1807.03748, 2018.
  33. Moment matching for multi-source domain adaptation. In Proceedings of the IEEE/CVF international conference on computer vision, pages 1406–1415, 2019.
  34. Structured domain randomization: Bridging the reality gap by context-aware synthetic data. In 2019 International Conference on Robotics and Automation (ICRA), pages 7249–7255. IEEE, 2019.
  35. Fishr: Invariant gradient variances for out-of-distribution generalization. In International Conference on Machine Learning, pages 18347–18377. PMLR, 2022.
  36. Advances in neural information processing systems. In In G. Tesauro & D. Touretzky & T. Leed (Eds.), Advances in Neural Information Processing Systems. Citeseer, 1995.
  37. Distributionally robust neural networks for group shifts: On the importance of regularization for worst-case generalization. arXiv preprint arXiv:1911.08731, 2019.
  38. Learning to optimize domain specific normalization for domain generalization. In European Conference on Computer Vision, pages 68–83. Springer, 2020.
  39. Gradient matching for domain generalization. arXiv preprint arXiv:2104.09937, 2021.
  40. Deep coral: Correlation alignment for deep domain adaptation. In European conference on computer vision, pages 443–450. Springer, 2016.
  41. Neuron coverage-guided domain generalization. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2022.
  42. What makes for good views for contrastive learning? Advances in Neural Information Processing Systems, 33:6827–6839, 2020.
  43. Domain randomization for transferring deep neural networks from simulation to the real world. In 2017 IEEE/RSJ international conference on intelligent robots and systems (IROS), pages 23–30. IEEE, 2017.
  44. Unbiased look at dataset bias. In CVPR 2011, pages 1521–1528. IEEE, 2011.
  45. Deep domain confusion: Maximizing for domain invariance. arXiv preprint arXiv:1412.3474, 2014.
  46. Vladimir N Vapnik. An overview of statistical learning theory. IEEE transactions on neural networks, 10(5):988–999, 1999.
  47. Deep hashing network for unsupervised domain adaptation. In Proceedings of the IEEE conference on computer vision and pattern recognition, pages 5018–5027, 2017.
  48. Generalizing to unseen domains via adversarial data augmentation. Advances in neural information processing systems, 31, 2018.
  49. Likang Wang. Dionysus: Recovering scene structures by dividing into semantic pieces.
  50. Ftso: Effective nas via first topology second operator. arXiv preprint arXiv:2303.12948, 2023.
  51. Is-mvsnet: Importance sampling-based mvsnet. In Computer Vision–ECCV 2022: 17th European Conference, Tel Aviv, Israel, October 23–27, 2022, Proceedings, Part XXXII, pages 668–683. Springer, 2022.
  52. Flora: dual-frequency loss-compensated real-time monocular 3d video reconstruction. In Proceedings of the AAAI Conference on Artificial Intelligence, volume 1, 2023.
  53. Learning from extrinsic and intrinsic supervisions for domain generalization. In European Conference on Computer Vision, pages 159–176. Springer, 2020.
  54. Understanding contrastive representation learning through alignment and uniformity on the hypersphere. In International Conference on Machine Learning, pages 9929–9939. PMLR, 2020.
  55. Exploring cross-image pixel contrast for semantic segmentation. In Proceedings of the IEEE/CVF International Conference on Computer Vision, pages 7303–7313, 2021.
  56. Dense contrastive learning for self-supervised visual pre-training. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 3024–3033, 2021.
  57. Propagate yourself: Exploring pixel-level consistency for unsupervised visual representation learning. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 16684–16693, 2021.
  58. A fourier-based framework for domain generalization. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 14383–14392, 2021.
  59. Improve unsupervised domain adaptation with mixup training. arXiv preprint arXiv:2001.00677, 2020.
  60. Pcl: Proxy-based contrastive learning for domain generalization. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 7097–7107, 2022.
  61. Substructure aware graph neural networks. In Proc. of AAAI, 2023.
  62. A simple graph neural network via layer sniffer. In ICASSP 2022-2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pages 5687–5691. IEEE, 2022.
  63. Adaptive risk minimization: Learning to adapt to domain shift. Advances in Neural Information Processing Systems, 34:23664–23678, 2021.
  64. Domain generalization with mixstyle. arXiv preprint arXiv:2104.02008, 2021.
Citations (9)
View on Semantic Scholar

Summary

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

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