Generate QR code
Open Access
Subscription Access
SpikeYOLO-RS: Improved Spike-Convolution Neural Network for Remote Sensing Image Object Detection
Abstract
This paper studies how to increase accuracy of SpikeYOLO for remote sensing (RS) images analysis, and proposes an improvement method. First, a dynamic membrane potential attenuation mechanism is constructed and the fixed attenuation factor is reconstructed into a learnable parameter. Then, the membrane potential is updated through vectorized parallel computing. Learnable residual weights are introduced to improve the feature fusion capability and; finally, the calculation flow is adjusted. On the RSOD remote sensing dataset, we obtained 96.8% mAP 50 and 64.8% mAP 50:95, which are 6.7 and 2.3% higher than the previous stateof-the-art SpikeYOLO, respectively. On the NWPU-VHR-10 dataset, we obtained 92.8% mAP 50, which is 1.5% higher than SpikeYOLO with the same architecture.
About the Authors
X. Wu
Belarusian State University
Belarus
Belarus
Minsk
S. V. Ablameyko
Belarusian State University;
United Institute of Informatics Problems of the National Academy of Sciences of Belarus
Belarus
Belarus
Minsk
References
1. S. C. Liu, K. C. Du, Y. J. Zheng, J. Chen, P. J. Du, X. H. Tong. Nat. Remote Sens. Bull., 27, N 9 (2023) 1975—1987, doi: 10.11834/jrs.20222199.
2. R. Girshick, J. Donahue, T. Darrell, J. Malik. IEEE Conf. Computer Vision and Pattern Recognition (2014) 580—587, https://doi.org/10.1109/CVPR.2014.81
3. R. Girshick. IEEE Int. Conf. Computer Vision (ICCV) (2015) 1440—1448, https://doi.org/10.1109/ ICCV.2015.169
4. S. Ren, K. He, R. Girshick, J. Sun. IEEE Transact. Pattern Analysis and Machine Intelligence, 39, N 6 (2017) 1137—1149, https://doi.org/10.1109/TPAMI.2016.2577031
5. K. He, G. Gkioxari, P. Dollár, R. Girshick. IEEE Int. Conf. Computer Vision (ICCV) (2017) 2980—2988, https://doi.org/10.1109/ICCV.2017.322
6. W. Liu, D. Anguelov, D. Erhan, C. Szegedy, S. Reed, C.-Y. Fu, A. C. Berg. In Computer Vision – ECCV, Springer International Publishing (2016) 21—37, https://doi.org/10.1007/978-3-319-46448-0_2
7. J. Redmon, S. Divvala, R. Girshick, A. Farhadi. IEEE Conf. Computer Vision and Pattern Recognition (CVPR) (2016) 779—788, https://doi.org/10.1109/CVPR.2016.91
8. S. Ghosh-Dastidar, H. Adeli. Int. J. Neural Systems, 19, N 4 (2009) 295—308, https://doi.org/10.1142/S0129065709002002
9. A. Tavanaei, M. Ghodrati, S. R. Kheradpisheh, T. Masquelier, A. Maida. Neural Networks, 111 (2019) 47—63, https://doi.org/10.1016/j.neunet.2018.12.002
10. G. Chen, G. Wang. IEEE Access, 8 (2020) 53427—53442, https://doi.org/10.1109/ACCESS.2020.2981346
11. J. Hou, W. Chen, G. Yang, L. Cong, X. Qi. 8th Asian Conf. Artificial Intelligence Technology (ACAIT) (2024) 745—749, https://doi.org/10.1109/ACAIT63902.2024.11022103
12. W. Maass. Neural Networks, 10, N 9 (1997) 1659—1671, https://doi.org/10.1016/S0893-6080(97)00011-7
13. P. A. Merolla, J. V. Arthur, R. Alvarez-Icaza, A. S. Cassidy, J. Sawada, F. Akopyan, B. L. Jackson, N. Imam, C. Guo, Y. Nakamura, B. Brezzo, I. Vo, S. K. Esser, R. Appuswamy, B. Taba, A. Amir, M. D. Flickner, W. P. Risk, R. Manohar, D. S. Modha. Science, 345, 6197 (2014) 668—673, https://doi.org/10.1126/science.1254642
14. P. U. Diehl, D. Neil, J. Binas, M. Cook, S.-C. Liu, M. Pfeiffer. Int. Joint Conference on Neural Networks (IJCNN) (2015) 1—8, https://doi.org/10.1109/IJCNN.2015.7280696
15. W. Fang, Z. Yu, Y. Chen, T. Huang, T. Masquelier, Y. Tian. arXiv: 2102.04159 (2022), https://arxiv.org/abs/2102.04159
16. Y. Lan, Y. Zhang, X. Ma, Y. Qu, Y. Fu. In 2023 IEEE/CVF Int. Conf. Computer Vision (ICCV) (2023) 9177—9186, https://doi.org/10.1109/ICCV51070.2023.00845
17. C. Lee, A. K. Kosta, A. Z. Zhu, K. Chaney, K. Daniilidis, K. Roy. arXiv: 2003.06696 (2020), https://arxiv.org/abs/2003.06696
18. Y. Li, S. Deng, X. Dong, S. Gu, Y. Ding. Int. J. Comp. Vision, 132, N 11 (2024), 3586—3609, https://doi.org/10.1007/s11263-024-02046-2
19. J. Ding, Z. Yu, Y. Tian, T. Huang. arXiv: 2105.11654 (2021), https://arxiv.org/abs/2105.11654
20. C. Stöckl, W. Maass. Nature Machine Intelligence, 3 (2021) 230—238, https://doi.org/10.1038/s42256-021-00311-4
21. S. Kim, S. Park, B. Na, S. Yoon. arXiv: 1903.06530 (2019), https://arxiv.org/abs/1903.06530
22. Q. Su, Y. Chou, Y. Hu, J. Li, S. Mei, Z. Zhang, G. Li. arXiv: 2307.11411 (2023), https://arxiv.org/abs/2307.11411
23. M. Yao, J. Hu, T. Hu, Y. Xu, Z. Zhou, Y. Tian, B. Xu, G. Li. The Twelfth Int. Conf. on Learning Representations, Vienna, May 07 2024 (2024), https://openreview.net/forum?id=1SIBN5Xyw7
24. X. Luo, M. Yao, Y. Chou, B. Xu, G. Li. arXiv: 2407.20708 (2024), https://arxiv.org/abs/2407.20708
25. G. Jocher, J. Qiu, A. Chaurasia. Ultralytics YOLO (Version 8.0.0) [Computer software] (2023), https://github.com/ultralytics/ultralytics
Review
For citations:
Wu X., Ablameyko S.V. SpikeYOLO-RS: Improved Spike-Convolution Neural Network for Remote Sensing Image Object Detection. Zhurnal Prikladnoii Spektroskopii. 2026;93(1):105-113. (In Russ.)
Views:
8
JATS XML
Email this article 