Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
110 tokens/sec
GPT-4o
56 tokens/sec
Gemini 2.5 Pro Pro
44 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

Source-Free Online Domain Adaptive Semantic Segmentation of Satellite Images under Image Degradation (2401.02113v1)

Published 4 Jan 2024 in cs.CV

Abstract: Online adaptation to distribution shifts in satellite image segmentation stands as a crucial yet underexplored problem. In this paper, we address source-free and online domain adaptation, i.e., test-time adaptation (TTA), for satellite images, with the focus on mitigating distribution shifts caused by various forms of image degradation. Towards achieving this goal, we propose a novel TTA approach involving two effective strategies. First, we progressively estimate the global Batch Normalization (BN) statistics of the target distribution with incoming data stream. Leveraging these statistics during inference has the ability to effectively reduce domain gap. Furthermore, we enhance prediction quality by refining the predicted masks using global class centers. Both strategies employ dynamic momentum for fast and stable convergence. Notably, our method is backpropagation-free and hence fast and lightweight, making it highly suitable for on-the-fly adaptation to new domain. Through comprehensive experiments across various domain adaptation scenarios, we demonstrate the robust performance of our method.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (15)
  1. “S&gda: An unsupervised domain adaptive semantic segmentation framework considering both imaging scene and geometric domain shifts,” IEEE Transactions on Geoscience and Remote Sensing, 2023.
  2. “Standardgan: Multi-source domain adaptation for semantic segmentation of very high resolution satellite images by data standardization,” in Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops, June 2020.
  3. “Universal domain adaptation for remote sensing image scene classification,” IEEE Transactions on Geoscience and Remote Sensing, vol. 61, pp. 1–15, 2023.
  4. “Source-free domain adaptation for cross-scene hyperspectral image classification,” in IGARSS 2022-2022 IEEE International Geoscience and Remote Sensing Symposium. IEEE, 2022, pp. 3576–3579.
  5. “Tent: Fully test-time adaptation by entropy minimization,” in International Conference on Learning Representations, 2021.
  6. “Revisiting batch normalization for practical domain adaptation,” arXiv preprint arXiv:1603.04779, 2016.
  7. “Domain adaptation based on correlation subspace dynamic distribution alignment for remote sensing image scene classification,” IEEE Transactions on Geoscience and Remote Sensing, vol. 58, no. 11, pp. 7920–7930, 2020.
  8. “Unsupervised domain adaptation for remote sensing image segmentation based on adversarial learning and self-training,” IEEE Geoscience and Remote Sensing Letters, vol. 20, pp. 1–5, 2023.
  9. “The norm must go on: dynamic unsupervised domain adaptation by normalization,” in Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2022, pp. 14765–14775.
  10. “Dynamically instance-guided adaptation: A backward-free approach for test-time domain adaptive semantic segmentation,” in Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2023, pp. 24090–24099.
  11. “Prototypical networks for few-shot learning,” Advances in neural information processing systems, vol. 30, 2017.
  12. “Transferrable prototypical networks for unsupervised domain adaptation,” in Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, 2019, pp. 2239–2247.
  13. “Deepglobe 2018: A challenge to parse the earth through satellite images,” in Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition Workshops, 2018, pp. 172–181.
  14. “Robustbench: a standardized adversarial robustness benchmark,” in Thirty-fifth Conference on Neural Information Processing Systems Datasets and Benchmarks Track (Round 2), 2021.
  15. “Rethinking atrous convolution for semantic image segmentation,” arXiv preprint arXiv:1706.05587, 2017.
User Edit Pencil Streamline Icon: https://streamlinehq.com
Authors (3)
  1. Fahim Faisal Niloy (12 papers)
  2. Kishor Kumar Bhaumik (8 papers)
  3. Simon S. Woo (42 papers)

Summary

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