[1] Wu A C[M]. Neural network and deep learning(2016).

[2] Zou Y B, Zhou W L, Chen X Z. Research of laser vision seam detection and tracking system based on depth hierarchical feature[J]. Chinese Journal of Lasers, 44, 0402009(2017).

[3] Qu L, Wang K R, Chen L L et al. Fast road detection based on RGBD images and convolutional neural network[J]. Acta Optica Sinica, 37, 1010003(2017).

[4] Gao H, Xue L Y. Back propagation neural network based on improved genetic algorithm fitting LED spectral model[J]. Laser & Optoelectronics Progress, 54, 072302(2017).

[5] Xie Y[M]. Deep learning & computer vision(2017).

[6] Su M H. Research on loss function in machine learning[D]. Xi’an: Northwest University(2015).

[7] Yuan L G, Xu Y, Hao Y Z. Image classification algorithm based on depth layer model[J]. Control Engineering of China, 25, 1882-1886(2018).

[8] Ren J J, Wang N. Research on cost function in artificial neural network[J]. Journal of Gansu Normal Colleges, 23, 61-63(2018).

[9] Do T T, Cai M, Pham T et al. -02-28)[2019-03-03]. https:∥arxiv., org/abs/1802, 10367(2018).

[10] Wang Y M, Tan X, Yang Y et al. -10-19)[2019-03-03]. https:∥arxiv., org/abs/1810, 09263(2018).

[11] Li Y, Wang G, Ji X Y et al. DeepIM: deep iterative matching for 6D pose estimation. [C]∥The European Conference on Computer Vision (ECCV), September 8-14, 2018, Munich, Germany. New York: IEEE, 683-698(2018).

[12] Jafari O H, Mustikovela S K, Pertsch K et al. -01-18)[2019-03-03]. https:∥arxiv., org/abs/1712, 01924(2018).

[13] Krull A, Brachmann E, Nowozin S et al. -04-11)[2019-03-03]. https:∥arxiv., org/abs/1612, 03779(2017).

[14] Cai P F, Duan C W. Image inpainting method based on optimal guidance rule coupled with distance constraint[J]. Journal of Electronic Measurement and Instrumentation, 32, 119-125(2018).

[15] Long X, Su H S, Liu G H et al. A face recognition algorithm based on angular distance loss function and convolutional neural network[J]. Laser & Optoelectronics Progress, 55, 121505(2018).

[16] Zhou Y. Partial label learning algorithms based on metric learning and max-loss function[D]. Dalian: Dalian University of Technology(2017).

[17] Zhou F Y, Jin L P, Dong J. Review of convolutional neural network[J]. Chinese Journal of Computers, 40, 1229-1251(2017).

[18] Tekin B, Sinha S N, Fua P. Real-time seamless single shot 6D object pose prediction. [C]∥Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, June 18-22, 2018, Salt Lake City, Utah. New York: IEEE, 292-301(2018).

[19] Rad M, Lepetit V. BB8: a scalable, accurate, robust to partial occlusion method for predicting the 3D poses of challenging objects without using depth. [C]∥2017 IEEE International Conference on Computer Vision (ICCV), October 22-29, 2017, Venice, Italy. New York: IEEE, 3848-3856(2017).

[20] Tang M, Djelouah A, Perazzi F et al. Normalized cut loss for weakly-supervised CNN segmentation. [C]∥Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, June 18-22, 2018, Salt Lake City, Utah. New York: IEEE, 1818-1827(2018).

[21] Alhaija H A, Mustikovela S K, Geiger A et al. -12-01)[2019-03-03]. https:∥arxiv., org/abs/1809, 04696(2018).

[22] Suzuki T, Kataoka H, Aoki Y et al. Anticipating traffic accidents with adaptive loss and large-scale incident DB. [C]∥Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, June 18-22, 2018, Salt Lake City, Utah. New York: IEEE, 3521-3529(2018).

[23] Kehl W, Manhardt F, Tombari F et al. SSD-6D: making RGB-based 3D detection and 6D pose estimation great again. [C]∥Proceedings of the IEEE International Conference on Computer Vision, October 22-29, 2017, Venice, Italy. New York: IEEE, 1521-1529(2017).

[24] Tekin B, Sinha S N, Fua P. Real-time seamless single shot 6D object pose prediction. [C]∥Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, June 18-22, 2018, Salt Lake City, Utah. New York: IEEE, 292-301(2018).