[1] SimonyanK, Zisserman A. Very deep convolutional networks for large-scale image recognition[J/OL]. ( 2015-04-10)[2019-06-16]. https:∥arxiv.org/abs/1409. 1556.

[2] He KM, Zhang XY, Ren SQ, et al. Deep residual learning for image recognition[C]∥2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), June 27-30, 2016, Las Vegas, NV, USA. New York: IEEE, 2016: 770- 778.

[3] GirshickR, DonahueJ, DarrellT, et al. Rich feature hierarchies for accurate object detection and semantic segmentation[C]∥2014 IEEE Conference on Computer Vision and Pattern Recognition, June 23-28, 2014, Columbus, OH, USA. New York: IEEE, 2014: 580- 587.

[4] LongJ, ShelhamerE, DarrellT. Fully convolutional networks for semantic segmentation[C]∥2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), June 7-12, 2015, Boston, MA, USA. New York: IEEE, 2015: 3431- 3440.

[5] HanS, PoolJ, TranJ, et al. Learning both weights and connections for efficient neural network[C]∥Advances in Neural Information Processing Systems, December 7-12, 2015, Montreal, Quebec, Canada. Canada: NIPS, 2015: 1135- 1143.

[6] SchererD, SchulzH, BehnkeS. Accelerating large-scale convolutional neural networks with parallel graphics multiprocessors[M] ∥Diamantaras K, Duch W, Iliadis L S. Artificial neural networks-ICANN 2010. Lecture notes in computer science. Berlin, Heidelberg: Springer, 2010, 6534: 82- 91.

[7] LiH, KadavA, DurdanovicI, et al. ( 2017-03-10)[2019-06-16]. https:∥arxiv.org/abs/1608. 08710.

[8] Hu HY, PengR, Tai YW, et al. ( 2016-07-12)[2019-06-16]. https:∥arxiv.org/abs/1607. 03250.

[9] 许勤. 灰色关联分析选区激光烧结成型研究[J]. 激光与光电子学进展, 2014, 51(12): 121406.

    Xu Q. Study on process parameters optimization of selective laser sintering with gray relational analysis[J]. Laser & Optoelectronics Progress, 2014, 51(12): 121406.

[10] 胡斌, 任曦骏, 叶斌, 等. 基于改进灰色关联分析的配电网低电压贡献度评价方法[J]. 电力电容器与无功补偿, 2018, 39(2): 90-94.

    Hu B, Ren X J, Ye B, et al. Evaluation method of low voltage contribution degree based on improved grey relation analysis in distribution network[J]. Power Capacitor & Reactive Power Compensation, 2018, 39(2): 90-94.

[11] MolchanovP, TyreeS, KarrasT, et al. ( 2017-06-08)[2019-06-16]. https:∥arxiv.org/abs/1611. 06440.

[12] 黄鸿, 何凯, 郑新磊, 等. 基于深度学习的高光谱图像空-谱联合特征提取[J]. 激光与光电子学进展, 2017, 54(10): 101001.

    Huang H, He K, Zheng X L, et al. Spatial-spectral feature extraction of hyperspectral image based on deep learning[J]. Laser & Optoelectronics Progress, 2017, 54(10): 101001.

[13] 陈清江, 李毅, 柴昱洲. 一种基于深度学习的多聚焦图像融合算法[J]. 激光与光电子学进展, 2018, 55(7): 071015.

    Chen Q J, Li Y, Chai Y Z. A multi-focus image fusion algorithm based on depth learning[J]. Laser & Optoelectronics Progress, 2018, 55(7): 071015.

[14] SinghP, Kadi V S R, Verma N, et al. Stability based filter pruning for accelerating deep CNNs[C]∥2019 IEEE Winter Conference on Applications of Computer Vision (WACV), January 7-11, 2019, Waikoloa Village, HI, USA. New York: IEEE, 2019: 1166- 1174.

[15] He YH, LinJ, Liu ZJ, et al. AMC: AutoML for model compression and acceleration on mobile devices[M] ∥Ferrari V, Hebert M, Sminchisescu C, et al. Computer Vision-ECCV 2018. Lecture Notes in Computer Science. Cham: Springer, 2018, 11211: 815- 832.

[16] 汪洪桥, 蔡艳宁, 付光远, 等. 基于图像序列的地面慢动多目标识别与跟踪[J]. 激光与光电子学进展, 2016, 53(5): 051501.

    Wang H Q, Cai Y N, Fu G Y, et al. Recognition and tracking of multiple slowly-moving ground targets based on image series[J]. Laser & Optoelectronics Progress, 2016, 53(5): 051501.

[17] SzegedyC, LiuW, Jia YQ, et al. Going deeper with convolutions[C]∥2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), June 7-12, 2015, Boston, MA, USA. New York: IEEE, 2015: 15523970.

[18] AbadiM, BarhamP, ChenJ, et al. Tensorflow: a system for large-scale machine learning[C]∥12th {USENIX} Symposium on Operating Systems Design and Implementation( {OSDI} 16), November 2-4, 2016, Savannah, GA. [S.l.: s.n.], 2016: 265- 283.

[19] 田青, 袁曈阳, 杨丹, 等. 基于暗通道去雾和深度学习的行人检测方法[J]. 激光与光电子学进展, 2018, 55(11): 111007.

    Tian Q, Yuan T Y, Yang D, et al. A pedestrian detection method based on dark channel defogging and deep learning[J]. Laser & Optoelectronics Progress, 2018, 55(11): 111007.