ABSTRACT
With the continuous development of earth observation technology, high-resolution satellite images with more detailed ground object information have become increasingly prevalent. As a result, multi-classification target detection has become one of the hot spots in this field. However, in reality, remote sensing images face the problem of limited samples under a long-tailed distribution, which hinders the model's ability to extract discriminative features for the target. To address this issue, we designed the TCLM module based on contrastive learning, aiming to address the difficulty of feature extraction for tail class targets. Meanwhile, there exists another issue: complex background noises also interfere with target feature extraction. To overcome this problem of background noise interference in complex remote sensing images, we propose the PARM module, which can help the model to focus on the target itself, thereby decreasing its attention on the background. Experimental results on the MSAR and DOTA datasets show that our method significantly improves detection performance.
- F. Liu, R. Chen, J. Zhang, K. Xing, H. Liu, and J. Qin, “R2yolox: A lightweight refined anchor-free rotated detector for object detection in aerial images,” IEEE Transactions on Geoscience and Remote Sensing, vol. 60, pp. 1–15, 2022.Google Scholar
- P. Shamsolmoali, M. Zareapoor, J. Chanussot, H. Zhou, and J. Yang, “Rotation equivariant feature image pyramid network for object de- tection in optical remote sensing imagery,” IEEE Transactions on Geoscience and Remote Sensing, vol. 60, pp. 1–14, 2022.Google ScholarCross Ref
- Z. Ren, B. Hou, Q. Wu, Z. Wen, and L. Jiao, “A distribution and structure match generative adversarial network for sar image classification,” IEEE Transactions on Geoscience and Remote Sensing, vol. 58, no. 6, pp. 3864–3880, 2020.Google ScholarCross Ref
- J. Geng, X. Deng, X. Ma, and W. Jiang, “Transfer learning for sar image classification via deep joint distribution adaptation networks,” IEEE Transactions on Geoscience and Remote Sensing, vol. 58, no. 8, pp. 5377–5392, 2020.Google ScholarCross Ref
- W. Xie, G. Ma, F. Zhao, H. Liu, and L. Zhang, “Polsar image classifica- tion via a novel semi-supervised recurrent complex-valued convolution neural network,” Neurocomputing, vol. 388, pp. 255–268, 2020.Google ScholarDigital Library
- J. Tan, C. Wang, B. Li, Q. Li, W. Ouyang, C. Yin, and J. Yan, “Equalization loss for long-tailed object recognition,” in Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, 2020, pp. 11 662–11 671.Google ScholarCross Ref
- B. Li, Y. Yao, J. Tan, G. Zhang, F. Yu, J. Lu, and Y. Luo, “Equalized focal loss for dense long-tailed object detection,” in Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2022, pp. 6990–6999.Google ScholarCross Ref
- Z. H. Jie Chen, B. W. Runfan Xia, L. S. Lei Sheng, and B. Yao., “Large- scale multi-class sar image target detection dataset-1.0[ol],” Journal of Radars, 2022.Google Scholar
- R. Xia, J. Chen, Z. Huang, H. Wan, B. Wu, L. Sun, B. Yao, H. Xiang, and M. Xing, “Crtranssar: A visual transformer based on contextual joint representation learning for sar ship detection,” Remote Sensing, vol. 14, no. 6, p. 1488, 2022.Google ScholarCross Ref
- G.-S. Xia, X. Bai, J. Ding, Z. Zhu, S. Belongie, J. Luo, M. Datcu, M. Pelillo, and L. Zhang, “Dota: A large-scale dataset for object detection in aerial images,” in Proceedings of the IEEE conference on computer vision and pattern recognition, 2018, pp. 3974–3983.Google ScholarCross Ref
Index Terms
- Improving the Long-tailed Remote Sensing Target Detection via Target-level Comparision
Recommendations
Target detection of remote sensing images based on deep learning method and system
AISS '21: Proceedings of the 3rd International Conference on Advanced Information Science and SystemAbstract: With the rapid growth of remote sensing image data, it is very important to find a way to extract and recognize the target quickly and accurately from the massive remote sensing data. In recent years, the development of deep learning has ...
A Remote Sensing Image Based Convolutional Neural Network for Target Detection of Electric Power
ICITEE '21: Proceedings of the 4th International Conference on Information Technologies and Electrical EngineeringAs the basic content of urban construction and development, electric power facilities target detection can guarantee the basic work of urban electricity safety. In the rapid development of remote sensing technology, there are more and more remote ...
Remote Sensing Target Detection Based on Improved YoloX
ICCVIT '23: Proceedings of the 2023 International Conference on Computer, Vision and Intelligent TechnologyThe identification and positioning of remotely sensed targets hold significant potential in various fields. Nonetheless, the detection and localisation of the algorithm face challenges due to the divergence of size, shape and spatial position ...
Comments