Papers
Topics
Authors
Recent
2000 character limit reached

Continual Domain Adversarial Adaptation via Double-Head Discriminators (2402.03588v1)

Published 5 Feb 2024 in cs.LG and cs.AI

Abstract: Domain adversarial adaptation in a continual setting poses a significant challenge due to the limitations on accessing previous source domain data. Despite extensive research in continual learning, the task of adversarial adaptation cannot be effectively accomplished using only a small number of stored source domain data, which is a standard setting in memory replay approaches. This limitation arises from the erroneous empirical estimation of $\gH$-divergence with few source domain samples. To tackle this problem, we propose a double-head discriminator algorithm, by introducing an addition source-only domain discriminator that are trained solely on source learning phase. We prove that with the introduction of a pre-trained source-only domain discriminator, the empirical estimation error of $\gH$-divergence related adversarial loss is reduced from the source domain side. Further experiments on existing domain adaptation benchmark show that our proposed algorithm achieves more than 2$\%$ improvement on all categories of target domain adaptation task while significantly mitigating the forgetting on source domain.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (63)
  1. A theory of learning from different domains. Machine learning, 79(1):151–175, 2010.
  2. On learning invariant representations for domain adaptation. In International Conference on Machine Learning, pages 7523–7532. PMLR, 2019.
  3. Domain-adversarial training of neural networks. The journal of machine learning research, 17(1):2096–2030, 2016.
  4. Adversarial multiple source domain adaptation. Advances in neural information processing systems, 31:8559–8570, 2018.
  5. Conditional adversarial domain adaptation. arXiv preprint arXiv:1705.10667, 2017.
  6. Bridging theory and algorithm for domain adaptation. In International Conference on Machine Learning, pages 7404–7413. PMLR, 2019.
  7. Il2m: Class incremental learning with dual memory. In Proceedings of the IEEE/CVF international conference on computer vision, pages 583–592, 2019.
  8. Maintaining discrimination and fairness in class incremental learning. In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, pages 13208–13217, 2020.
  9. Learning a unified classifier incrementally via rebalancing. In Proceedings of the IEEE/CVF conference on Computer Vision and Pattern Recognition, pages 831–839, 2019.
  10. End-to-end incremental learning. In Proceedings of the European conference on computer vision (ECCV), pages 233–248, 2018.
  11. Large scale incremental learning. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 374–382, 2019.
  12. Adaptive aggregation networks for class-incremental learning. In Proceedings of the IEEE/CVF conference on Computer Vision and Pattern Recognition, pages 2544–2553, 2021.
  13. On tiny episodic memories in continual learning. arXiv preprint arXiv:1902.10486, 2019.
  14. Hrn: A holistic approach to one class learning. Advances in neural information processing systems, 33:19111–19124, 2020.
  15. Maximum classifier discrepancy for unsupervised domain adaptation. In Proceedings of the IEEE conference on computer vision and pattern recognition, pages 3723–3732, 2018.
  16. Pseudo-labeling and confirmation bias in deep semi-supervised learning. In 2020 International Joint Conference on Neural Networks (IJCNN), pages 1–8. IEEE, 2020.
  17. Meta pseudo labels. In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, pages 11557–11568, 2021.
  18. Dine: Domain adaptation from single and multiple black-box predictors. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 8003–8013, 2022.
  19. Source-free domain adaptation via distribution estimation. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 7212–7222, 2022.
  20. Francois Fleuret et al. Uncertainty reduction for model adaptation in semantic segmentation. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 9613–9623, 2021.
  21. Leveraging unsupervised data and domain adaptation for deep regression in low-cost sensor calibration. arXiv preprint arXiv:2210.00521, 2022.
  22. Universal source-free domain adaptation. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 4544–4553, 2020.
  23. Model adaptation: Unsupervised domain adaptation without source data. In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, pages 9641–9650, 2020.
  24. Vdm-da: Virtual domain modeling for source data-free domain adaptation. IEEE Transactions on Circuits and Systems for Video Technology, 32(6):3749–3760, 2021.
  25. Exploring domain-invariant parameters for source free domain adaptation. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 7151–7160, 2022.
  26. Adaptive adversarial network for source-free domain adaptation. In Proceedings of the IEEE/CVF international conference on computer vision, pages 9010–9019, 2021.
  27. Generalized source-free domain adaptation. In Proceedings of the IEEE/CVF International Conference on Computer Vision, pages 8978–8987, 2021.
  28. Sofa: Source-data-free feature alignment for unsupervised domain adaptation. In Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision, pages 474–483, 2021.
  29. Robust continual test-time adaptation: Instance-aware bn and prediction-balanced memory. arXiv preprint arXiv:2208.05117, 2022.
  30. Efficient test-time model adaptation without forgetting. In International conference on machine learning, pages 16888–16905. PMLR, 2022.
  31. Fedmm: A communication efficient solver for federated adversarial domain adaptation. In Proceedings of the 2023 International Conference on Autonomous Agents and Multiagent Systems, pages 1808–1816, 2023.
  32. Federated adversarial domain adaptation. In International Conference on Learning Representations, 2019.
  33. Progressive neural networks. arXiv preprint arXiv:1606.04671, 2016.
  34. Online incremental feature learning with denoising autoencoders. In Artificial intelligence and statistics, pages 1453–1461. PMLR, 2012.
  35. Adanet: Adaptive structural learning of artificial neural networks. In International conference on machine learning, pages 874–883. PMLR, 2017.
  36. Lifelong learning with dynamically expandable networks. In International Conference on Learning Representations, 2018.
  37. Continual segment: towards a single, unified and accessible continual segmentation model of 143 whole-body organs in ct scans. arXiv preprint arXiv:2302.00162, 2023.
  38. Gradient episodic memory for continual learning. Advances in neural information processing systems, 30, 2017.
  39. Efficient lifelong learning with a-gem. In International Conference on Learning Representations, 2018.
  40. Continual learning with tiny episodic memories. In Workshop on Multi-Task and Lifelong Reinforcement Learning, 2019.
  41. Learning to learn without forgetting by maximizing transfer and minimizing interference. In International Conference on Learning Representations, 2018.
  42. Remind your neural network to prevent catastrophic forgetting. In Computer Vision–ECCV 2020: 16th European Conference, Glasgow, UK, August 23–28, 2020, Proceedings, Part VIII 16, pages 466–483. Springer, 2020.
  43. Gdumb: A simple approach that questions our progress in continual learning. In Computer Vision–ECCV 2020: 16th European Conference, Glasgow, UK, August 23–28, 2020, Proceedings, Part II 16, pages 524–540. Springer, 2020.
  44. Learning without forgetting. IEEE transactions on pattern analysis and machine intelligence, 40(12):2935–2947, 2017.
  45. Overcoming catastrophic forgetting in neural networks. Proceedings of the national academy of sciences, 114(13):3521–3526, 2017.
  46. Continual learning through synaptic intelligence. In International conference on machine learning, pages 3987–3995. PMLR, 2017.
  47. Online continual learning under extreme memory constraints. In Computer Vision–ECCV 2020: 16th European Conference, Glasgow, UK, August 23–28, 2020, Proceedings, Part XXVIII 16, pages 720–735. Springer, 2020.
  48. Continual adaptation of visual representations via domain randomization and meta-learning. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 4443–4453, 2021.
  49. Progressive voronoi diagram subdivision enables accurate data-free class-incremental learning. In The Eleventh International Conference on Learning Representations, 2022.
  50. Self-labelling via simultaneous clustering and representation learning. arXiv preprint arXiv:1911.05371, 2019.
  51. Unsupervised domain adaptation of black-box source models. arXiv preprint arXiv:2101.02839, 2021.
  52. Do we really need to access the source data? source hypothesis transfer for unsupervised domain adaptation. In International Conference on Machine Learning, pages 6028–6039. PMLR, 2020.
  53. Distilling the knowledge in a neural network. arXiv preprint arXiv:1503.02531, 2015.
  54. Analyzing the effectiveness and applicability of co-training. In Proceedings of the ninth international conference on Information and knowledge management, pages 86–93, 2000.
  55. Understanding self-training for gradual domain adaptation. In International Conference on Machine Learning, pages 5468–5479. PMLR, 2020.
  56. Unsupervised domain adaptation by backpropagation. In International conference on machine learning, pages 1180–1189. PMLR, 2015.
  57. Domain adaptation: Learning bounds and algorithms. arXiv preprint arXiv:0902.3430, 2009.
  58. Jonathan J. Hull. A database for handwritten text recognition research. IEEE Transactions on pattern analysis and machine intelligence, 16(5):550–554, 1994.
  59. Adapting visual category models to new domains. In European conference on computer vision, pages 213–226. Springer, 2010.
  60. Deep hashing network for unsupervised domain adaptation. In Proceedings of the IEEE conference on computer vision and pattern recognition, pages 5018–5027, 2017.
  61. Deep residual learning for image recognition. In Proceedings of the IEEE conference on computer vision and pattern recognition, pages 770–778, 2016.
  62. Imagenet large scale visual recognition challenge. International journal of computer vision, 115(3):211–252, 2015.
  63. Foundations of machine learning. MIT press, 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

Whiteboard

Open Problems

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

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

Continue Learning

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

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

Collections

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

User Circle Single Streamline Icon: https://streamlinehq.com Sign Up