A Novel Small Target Detection Strategy: Location Feature Extraction in the Case of Self-Knowledge Distillation
-
Published:2023-03-14
Issue:6
Volume:13
Page:3683
-
ISSN:2076-3417
-
Container-title:Applied Sciences
-
language:en
-
Short-container-title:Applied Sciences
Author:
Liu Gaohua1, Li Junhuan2, Yan Shuxia2, Liu Rui3
Affiliation:
1. School of Electrical and Information Engineering, Tianjin University, Tianjin 300072, China 2. School of Electronics and Information Engineering, Tiangong University, Tianjin 300387, China 3. School of Software, Tiangong University, Tianjin 300387, China
Abstract
Small target detection has always been a hot and difficult point in the field of target detection. The existing detection network has a good effect on conventional targets but a poor effect on small target detection. The main challenge is that small targets have few pixels and are widely distributed in the image, so it is difficult to extract effective features, especially in the deeper neural network. A novel plug-in to extract location features of the small target in the deep network was proposed. Because the deep network has a larger receptive field and richer global information, it is easier to establish global spatial context mapping. The plug-in named location feature extraction establishes the spatial context mapping in the deep network to obtain the global information of scattered small targets in the deep feature map. Additionally, the attention mechanism can be used to strengthen attention to the spatial information. The comprehensive effect of the above two can be utilized to realize location feature extraction in the deep network. In order to improve the generalization of the network, a new self-distillation algorithm was designed for pre-training that could work under self-supervision. The experiment was conducted on the public datasets (Pascal VOC and Printed Circuit Board Defect dataset) and the self-made dedicated small target detection dataset, respectively. According to the diagnosis of the false-positive error distribution, the location error was significantly reduced, which proved the effectiveness of the plug-in proposed for location feature extraction. The mAP results can prove that the detection effect of the network applying the location feature extraction strategy is much better than the original network.
Funder
China Postdoctoral Science Foundation
Subject
Fluid Flow and Transfer Processes,Computer Science Applications,Process Chemistry and Technology,General Engineering,Instrumentation,General Materials Science
Reference63 articles.
1. He, K., Gkioxari, G., Dollár, P., and Girshick, R. (2017, January 22–29). Mask R-CNN. Proceedings of the IEEE International Conference on Computer Vision, Venice, Italy. 2. Cai, Z., and Vasconcelos, N. (2018, January 18–22). Cascade R-CNN: Delving into high quality object detection. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Salt Lake City, UT, USA. 3. Chen, K., Pang, J., Wang, J., Xiong, Y., Li, X., Sun, S., Feng, W., Liu, Z., Shi, J., and Ouyang, W. (2019, January 15–20). Hybrid task cascade for instance segmentation. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, Long Beach, CA, USA. 4. Lin, T.Y., Maire, M., Belongie, S., Hays, J., Perona, P., Ramanan, D., Dollár, P., and Zitnick, C.L. (2014, January 6–12). Microsoft COCO: Common objects in contex. Proceedings of the Computer Vision–ECCV 2014: 13th European Conference, Zurich, Switzerland. 5. Chen, C., Liu, M.Y., Tuzel, O., and Xiao, J. (2016, January 20–24). R-CNN for small object detection. Proceedings of the Computer Vision–ACCV 2016: 13th Asian Conference on Computer Vision, Taipei, Taiwan.
|
|