Page 495 - 《软件学报》2025年第10期

4892 软件学报 2025 年第 36 卷第 10 期

[33] He XF, Niyogi P. Locality preserving projections. In: Proc. of the 17th Int’l Conf. on Neural Information Processing Systems. Whistler:
MIT Press, 2004. 153–160.
[34] Roweis ST, Saul LK. Nonlinear dimensionality reduction by locally linear embedding. Science, 2000, 290(5500): 2323–2326. [doi: 10.
1126/science.290.5500.2323]
[35] Tenenbaum JB, De Silva V, Langford JC. A global geometric framework for nonlinear dimensionality reduction. Science, 2000,
290(5500): 2319–2323. [doi: 10.1126/science.290.5500.2319]
[36] Yu FX, Kumar S, Gong YC, Chang SF. Circulant binary embedding. In: Proc. of the 31st Int’l Conf. on Machine Learning. 2014.
946–954.
[37] Russakovsky O, Deng J, Su H, Krause J, Satheesh S, Ma SA, Huang ZH, Karpathy A, Khosla A, Bernstein M, Berg AC, Fei-Fei L.
ImageNet large scale visual recognition challenge. Int’l Journal of Computer Vision, 2015, 115(3): 211–252. [doi: 10.1007/s11263-015-
0816-y]
[38] Boyd S, Parikh N, Chu E, Peleato B, Eckstein J. Distributed optimization and statistical learning via the alternating direction method of
multipliers. Foundations and Trends® in Machine Learning, 2011, 3(1): 1–122. [doi: 10.1561/2200000016]
[39] McDonnell MD. Training wide residual networks for deployment using a single bit for each weight. arXiv:1802.08530, 2018.
[40] Krizhevsky A. Learning multiple layers of features from tiny images [MS. Thesis]. Toronto: Department of Computer Science, University
of Toronto, 2009.
[41] Everingham M, Van Gool L, Williams CKI, Winn J, Zisserman A. The PASCAL visual object classes (VOC) challenge. Int’l Journal of
Computer Vision, 2010, 88(2): 303–338. [doi: 10.1007/s11263-009-0275-4]
[42] Liu W, Anguelov D, Erhan D, Szegedy C, Reed S, Fu CY, Berg AC. SSD: Single shot MultiBox detector. In: Proc. of the 14th European
Conf. on Computer Vision. Amsterdam: Springer, 2016. 21–37. [doi: 10.1007/978-3-319-46448-0_2]
[43] Xu ZH, Lin MB, Liu JZ, Chen J, Shao L, Gao Y, Tian YH, Ji RR. ReCU: Reviving the dead weights in binary neural networks. In: Proc.
of the 2021 IEEE/CVF Int’l Conf. on Computer Vision (ICCV). Montreal: IEEE, 2021. 5178–5188. [doi: 10.1109/ICCV48922.2021.
00515]
[44] Liu CL, Ding WR, Xia X, Hu Y, Zhang BC, Liu JZ, Zhuang BH, Guo GD. RBCN: Rectified binary convolutional networks for
enhancing the performance of 1-bit DCNNs. In: Proc. of the 28th Int’l Joint Conf. on Artificial Intelligence. Macao: AAAI Press, 2019.
854–860.
[45] Chen HL, Zhuo L, Zhang BC, Zheng XW, Liu JZ, Ji RR, Doermann D, Guo GD. Binarized neural architecture search for efficient object
recognition. Int’l Journal of Computer Vision, 2021, 129(2): 501–516. [doi: 10.1007/s11263-020-01379-y]
[46] Qin HT, Gong RH, Liu XL, Shen MZ, Wei ZR, Yu FW, Song JK. Forward and backward information retention for accurate binary neural
networks. In: Proc. of the 2020 IEEE/CVF Conf. on Computer Vision and Pattern Recognition (CVPR). Seattle: IEEE, 2020. 2247–2256.
[doi: 10.1109/CVPR42600.2020.00232]

附中文参考文献:
[11] 龚成, 卢冶, 代素蓉, 刘方鑫, 陈新伟, 李涛. 一种超低损失的深度神经网络量化压缩方法. 软件学报, 2021, 32(8): 2391–2407. http://
www.jos.org.cn/1000-9825/6189.htm [doi: 10.13328/j.cnki.jos.006189]
[15] 胡杰. 卷积神经网络的结构优化与量化加速研究 [博士学位论文]. 北京: 中国科学院软件研究所, 2023.

韩凯(1993－), 男, 博士生, CCF 学生会员, 主要 吴恩华(1947－), 男, 博士, 研究员, CCF 会士, 主
研究领域为深度学习, 计算机视觉. 要研究领域为计算机图形学, 虚拟现实, 机器
学习.

刘传建(1986－), 男, 博士, 主要研究领域为深度
学习, 计算机视觉.