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

Diversity-aware Buffer for Coping with Temporally Correlated Data Streams in Online Test-time Adaptation (2401.00989v1)

Published 2 Jan 2024 in cs.CV

Abstract: Since distribution shifts are likely to occur after a model's deployment and can drastically decrease the model's performance, online test-time adaptation (TTA) continues to update the model during test-time, leveraging the current test data. In real-world scenarios, test data streams are not always independent and identically distributed (i.i.d.). Instead, they are frequently temporally correlated, making them non-i.i.d. Many existing methods struggle to cope with this scenario. In response, we propose a diversity-aware and category-balanced buffer that can simulate an i.i.d. data stream, even in non-i.i.d. scenarios. Combined with a diversity and entropy-weighted entropy loss, we show that a stable adaptation is possible on a wide range of corruptions and natural domain shifts, based on ImageNet. We achieve state-of-the-art results on most considered benchmarks.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (19)
  1. Dataset shift in machine learning, Mit Press, 2008.
  2. “On interaction between augmentations and corruptions in natural corruption robustness,” Advances in Neural Information Processing Systems, vol. 34, 2021.
  3. “Tent: Fully test-time adaptation by entropy minimization,” in International Conference on Learning Representations, 2021.
  4. “Gradual test-time adaptation by self-training and style transfer,” arXiv preprint arXiv:2208.07736, 2022.
  5. “Towards stable test-time adaptation in dynamic wild world,” in The Eleventh International Conference on Learning Representations, 2023.
  6. “Note: Robust continual test-time adaptation against temporal correlation,” Advances in Neural Information Processing Systems, vol. 35, pp. 27253–27266, 2022.
  7. “Robust test-time adaptation in dynamic scenarios,” in Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2023, pp. 15922–15932.
  8. “Parameter-free online test-time adaptation,” in Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2022, pp. 8344–8353.
  9. “Efficient test-time model adaptation without forgetting,” in International conference on machine learning. PMLR, 2022, pp. 16888–16905.
  10. “Universal test-time adaptation through weight ensembling, diversity weighting, and prior correction,” in Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision, 2024, pp. 2555–2565.
  11. “Test-time training with self-supervision for generalization under distribution shifts,” in International Conference on Machine Learning. PMLR, 2020, pp. 9229–9248.
  12. “Continual test-time domain adaptation,” in Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2022, pp. 7201–7211.
  13. “Robust mean teacher for continual and gradual test-time adaptation,” in Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2023, pp. 7704–7714.
  14. “Benchmarking neural network robustness to common corruptions and perturbations,” arXiv preprint arXiv:1903.12261, 2019.
  15. “The many faces of robustness: A critical analysis of out-of-distribution generalization,” in Proceedings of the IEEE/CVF International Conference on Computer Vision, 2021, pp. 8340–8349.
  16. “Learning robust global representations by penalizing local predictive power,” Advances in Neural Information Processing Systems, vol. 32, 2019.
  17. “Moment matching for multi-source domain adaptation,” in Proceedings of the IEEE/CVF international conference on computer vision, 2019, pp. 1406–1415.
  18. “An image is worth 16x16 words: Transformers for image recognition at scale,” arXiv preprint arXiv:2010.11929, 2020.
  19. “Contrastive test-time adaptation,” in Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2022, pp. 295–305.
User Edit Pencil Streamline Icon: https://streamlinehq.com
Authors (4)
  1. Mario Döbler (10 papers)
  2. Florian Marencke (1 paper)
  3. Robert A. Marsden (8 papers)
  4. Bin Yang (320 papers)
Citations (2)

Summary

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