Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
139 tokens/sec
GPT-4o
47 tokens/sec
Gemini 2.5 Pro Pro
43 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

Simplifying Two-Stage Detectors for On-Device Inference in Remote Sensing (2404.07405v1)

Published 11 Apr 2024 in cs.CV

Abstract: Deep learning has been successfully applied to object detection from remotely sensed images. Images are typically processed on the ground rather than on-board due to the computation power of the ground system. Such offloaded processing causes delays in acquiring target mission information, which hinders its application to real-time use cases. For on-device object detection, researches have been conducted on designing efficient detectors or model compression to reduce inference latency. However, highly accurate two-stage detectors still need further exploitation for acceleration. In this paper, we propose a model simplification method for two-stage object detectors. Instead of constructing a general feature pyramid, we utilize only one feature extraction in the two-stage detector. To compensate for the accuracy drop, we apply a high pass filter to the RPN's score map. Our approach is applicable to any two-stage detector using a feature pyramid network. In the experiments with state-of-the-art two-stage detectors such as ReDet, Oriented-RCNN, and LSKNet, our method reduced computation costs upto 61.2% with the accuracy loss within 2.1% on the DOTAv1.5 dataset. Source code will be released.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (27)
  1. On-board, real-time preprocessing system for optical remote-sensing imagery. Sensors, 18(5):1328, 2018.
  2. On-board multi-class geospatial object detection based on convolutional neural network for high resolution remote sensing images. Remote Sensing, 15(16):3963, 2023.
  3. Opportunities and challenges of ai on satellite processing units. In Proceedings of the 19th ACM international conference on computing Frontiers, pages 221–224, 2022.
  4. Large selective kernel network for remote sensing object detection. arxiv 2023. arXiv preprint arXiv:2303.09030.
  5. Spatial transform decoupling for oriented object detection. arXiv preprint arXiv:2308.10561, 2023.
  6. Oriented r-cnn for object detection. In Proceedings of the IEEE/CVF international conference on computer vision, pages 3520–3529, 2021.
  7. Robust real-time object detection based on deep learning for very high resolution remote sensing images. In IGARSS 2019-2019 IEEE International Geoscience and Remote Sensing Symposium, pages 1314–1317. IEEE, 2019.
  8. A survey of model compression strategies for object detection. Multimedia Tools and Applications, pages 1–72, 2023.
  9. You only look one-level feature. In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, pages 13039–13048, 2021.
  10. Point2rbox: Combine knowledge from synthetic visual patterns for end-to-end oriented object detection with single point supervision. arXiv preprint arXiv:2311.14758, 2023.
  11. Dota: A large-scale dataset for object detection in aerial images. In Proceedings of the IEEE conference on computer vision and pattern recognition, pages 3974–3983, 2018.
  12. Focal loss for dense object detection. In Proceedings of the IEEE international conference on computer vision, pages 2980–2988, 2017.
  13. Redet: A rotation-equivariant detector for aerial object detection. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 2786–2795, 2021.
  14. Probabilistic two-stage detection. arXiv preprint arXiv:2103.07461, 2021.
  15. A comprehensive review of yolo: From yolov1 to yolov8 and beyond. arXiv preprint arXiv:2304.00501, 2023.
  16. Dynamic head: Unifying object detection heads with attentions. In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, pages 7373–7382, 2021.
  17. Arbitrary-oriented scene text detection via rotation proposals. IEEE transactions on multimedia, 20(11):3111–3122, 2018.
  18. Learning roi transformer for oriented object detection in aerial images. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 2849–2858, 2019.
  19. Rtmdet: An empirical study of designing real-time object detectors. arXiv preprint arXiv:2212.07784, 2022.
  20. Rich feature hierarchies for accurate object detection and semantic segmentation. In Proceedings of the IEEE conference on computer vision and pattern recognition, pages 580–587, 2014.
  21. Ross Girshick. Fast r-cnn. In Proceedings of the IEEE international conference on computer vision, pages 1440–1448, 2015.
  22. Faster r-cnn: Towards real-time object detection with region proposal networks. Advances in neural information processing systems, 28, 2015.
  23. You only look once: Unified, real-time object detection. In Proceedings of the IEEE conference on computer vision and pattern recognition, pages 779–788, 2016.
  24. Yolo9000: better, faster, stronger. In Proceedings of the IEEE conference on computer vision and pattern recognition, pages 7263–7271, 2017.
  25. Feature pyramid networks for object detection. In Proceedings of the IEEE conference on computer vision and pattern recognition, pages 2117–2125, 2017.
  26. Objects as points. arXiv preprint arXiv:1904.07850, 2019.
  27. Mmrotate: A rotated object detection benchmark using pytorch. In Proceedings of the 30th ACM International Conference on Multimedia, 2022.

Summary

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

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