[2] [2] Chen Bolin, Li Haodong, Luo Weiqi, et al. Image processing operations identification via convoluti- onal neural network[J]. Science China (Informati- on Sciences), 2020, 63(03): 275-281.

[4] [4] Shi Wenling, Du Huiqian, Mei Wenbo. Novel Ch- annel Attention Residual Network for Single Image Super-Resolution[J]. Journal of Beijing Institute of Technology, 2020, 29(03): 345-353.

[6] [6] D Xinwu, S Laiqiang, L Pengfei, et al. A method for detecting the quality of cotton seeds based on an improved ResNet50 model[J]. PloS one, 2023, 18(2): e0273057-e0273057.

[7] [7] L Min, L Kun, H Wujie, et al. Feature enhancement modules applied to a feature pyramid network for object detection[J]. Pattern Analysis and Applicat- ions, 2023, 26(2): 617-629.

[11] [11] Chen Z, Liang Y, Yu Z B, et al. TO-YOLOX: a pure CNN tiny object detection model for remote sensing images[J]. International Journal of Digital Earth, 2023, 16(1): 3882-3904.

[14] [14] H Hongyuan, Y Zhijiao, C Huayu, et al. Fast detection method for prostate cancer cells based on an integrated Res-Net50 and YoloV5 framework[J]. Computer Methods and Programs in Biomedi- cine, 2022, 226: 107184-107184.

[16] [16] Yongkun S, Sean S, Miles B, et al. Physics of Failure Based Reliability Model of High-Power InGaAs-AlGaAs Strained QW Lasers Prone to C- OBD Failure[J]. High-Power Diode Laser Technology XVIII, 2020, 11262.

[17] [17] Sin Y, Lingley Z, Ayvazian T, et al. Catastrophic Optical Bulk Damage - A New Failure Mode in High-Power In-GaAs-AlGaAs Strained Quantum Well Lasers[J]. MRS Advances, 2018, 3(57-58): 3329-3345.

[18] [18] Lee, J. K, Park, et al. Improvement of catastrophic optical damage (COD) level for high-power 0.98-m GaInAs-GaInP laser[J]. Photonics Technology Letters, IEEE, 1998, 10(9): 1226-1228.