[8] [8] McClelland J L, Rumelhart D E. Distributed memory and the representation of general and specific information[J]. Journal of Experimental Psychology: General, 1985, 114(2): 159.

[9] [9] Zhou A, Yao A, Guo Y, et al. Incremental network quantization: Towards lossless CNNs with low-precision weights[EB]. arXiv: 1702.03044, 2017.

[10] [10] Zhang X Y, Zou J H, He K M, et al. Accelerating very deep convolutional networks for classification and detection[J]. IEEE Transactions on Pattern Analysis & Machine Intelligence, 2015, 38(10): 1943-1955.

[11] [11] Kim J, Park S U, Kwak N. Paraphrasing complex network: Network compression via factor transfer[C]//32nd Advances in Neural Information Processing Systems, 2018: 2760-2769.

[12] [12] Anil R, Pereyra G, Passos A, et al. Large scale distributed neural network training through online distillation[EB]. arXiv: 1804.03235, 2018.

[13] [13] He Y, Kang G L, Dong X Y, et al. Soft filter pruning for accelerating deep convolutional neural networks[EB]. arXiv: 1808.06866, 2018.

[14] [14] Bochkovskiy A, Wang C Y, Liao H. YOLOv4: Optimal speed and accuracy of object detection[EB]. arXiv: 2004.10934, 2020.

[15] [15] Msonda P, Uymaz S A, Karaaa S. Spatial pyramid pooling in deep convolutional networks for automatic tuberculosis diagnosis[J]. International Information and Engineering Technology Association, 2020, 37(6): 1075-1084.

[16] [16] Liu S, Qi L F, Qin H F, et al. Path aggregation network for instance segmentation[C]//IEEE Conference on Computer Vision and Pattern Recognition, 2018: 8759-8768.

[17] [17] Ding X H, Zhang X Y, Ma N, et al. RepVGG: Making VGG-style ConvNets great again[C]//IEEE Conference on Computer Vision and Pattern Recognition, 2021: 13728- 13737.