[1] [1] NIU Qian. Research on surface defect detection technology of diode glass shell[D]. Mianyang: Southwest University of Science and Technology, 2018.

[2] [2] GIRSHICK R. Fast R-CNN[C]//2015 IEEE International Conference on Computer Vision (ICCV). Santiago: IEEE, 2016: 1440-1448.

[3] [3] GIRSHICK R, DONAHUE J, DARRELL T, et al. Rich feature hierarchies for accurate object detection and semantic segmentation[C]//2014 IEEE Conference on Computer Vision and Pattern Recognition. Columbus: IEEE, 2014: 580-587.

[5] [5] LIU W, ANGUELOV D, ERHAN D, et al. SSD: single shot multibox detector[EB/OL]. (2016-12-29) [2022-3-2]. https://arxiv.org/abs/1512.02325v1.

[6] [6] REDMON J, DIVVALA S, GIRSHICK R, et al. You only look once: unified, real-time object detection[C]//2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). Las Vegas: IEEE, 2016: 779-788.

[7] [7] REDMON J, FARHADI A. YOLO9000: better, faster, stronger[C]//2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). Honolulu: IEEE, 2017: 6517-6525.

[8] [8] REDMON J, FARHADI A. YOLOv3: an incremental improvement[EB/OL]. (2018-04-08) [2022-3-2]. https://arxiv.org/abs/1804.02767.

[9] [9] BOCHKOVSKIY A, WANG C Y, LIAO H Y M. YOLOv4: optimal speed and accuracy of object detection[EB/OL]. (2020-04-23) [2022-3-2]. https://arxiv.org/abs/2004.10934.

[13] [13] HUANG G, LIU Z, VAN DER MAATEN L, et al. Densely connected convolutional networks[C]//2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). Honolulu: IEEE, 2017: 2261-2269.

[14] [14] TAN M X, PANG R M, LE Q V. EfficientDet: scalable and efficient object detection[C]//2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). Seattle: IEEE, 2020: 10778-10787.

[15] [15] LIN T Y, GOYAL P, GIRSHICK R, et al. Focal loss for dense object detection[C]//2017 IEEE International Conference on Computer Vision (ICCV). Venice: IEEE, 2017: 2999-3007.