Page 494 - 《软件学报》2025年第10期

韩凯 等: 用于二值神经网络的加宽和收缩机制 4891

[9] Zhou SC, Wu YX, Ni ZK, Zhou XY, Wen H, Zou YH. DoReFa-Net: Training low bitwidth convolutional neural networks with low
bitwidth gradients. arXiv:1606.06160, 2018.
[10] Hubara I, Courbariaux M, Soudry D, El-Yaniv R, Bengio Y. Binarized neural networks. In: Proc. of the 30th Int’l Conf. on Neural
Information Processing Systems. Barcelona: Curran Associates Inc., 2016. 4114–4122.
[11] Gong C, Lu Y, Dai SR, Liu FX, Chen XW, Li T. Ultra-low loss quantization method for deep neural network compression. Ruan Jian
Xue Bao/Journal of Software, 2021, 32(8): 2391–2407 (in Chinese with English abstract). http://www.jos.org.cn/1000-9825/6189.htm
[doi: 10.13328/j.cnki.jos.006189]
[12] Hinton G, Vinyals O, Dean J. Distilling the knowledge in a neural network. arXiv:1503.02531, 2015.
[13] Sandler M, Howard A, Zhu ML, Zhmoginov A, Chen LC. MobileNetV2: Inverted residuals and linear bottlenecks. In: Proc. of the 2018
IEEE/CVF Conf. on Computer Vision and Pattern Recognition. Salt Lake City: IEEE, 2018. 4510–4520. [doi: 10.1109/CVPR.2018.
00474]
[14] Han K, Wang YH, Tian Q, Guo JY, Xu CJ, Xu C. GhostNet: More features from cheap operations. In: Proc. of the 2020 IEEE/CVF Conf.
on Computer Vision and Pattern Recognition. Seattle: IEEE, 2020. 1577–1586. [doi: 10.1109/CVPR42600.2020.00165]
[15] Hu J. Architecture optimization and quantization acceleration of convolutional neural networks [Ph.D. Thesis]. Beijing: Institute of
Software, Chinese Academy of Sciences, 2023 (in Chinese with English abstract).
[16] Zhang DQ, Yang JL, Ye DQ, Hua G. LQ-Nets: Learned quantization for highly accurate and compact deep neural networks. In: Proc. of
the 15th European Conf. on Computer Vision (ECCV). Munich: Springer, 2018. 373–390. [doi: 10.1007/978-3-030-01237-3_23]
[17] Lin MB, Ji RR, Xu ZH, Zhang BC, Wang Y, Wu YJ, Huang FY, Lin CW. Rotated binary neural network. In: Proc. of the 34th Int’l Conf.
on Neural Information Processing Systems. Vancouver: Curran Associates Inc., 2020. 7474–7485.
[18] Han S, Mao HZ, Dally WJ. Deep compression: Compressing deep neural networks with pruning, trained quantization and Huffman
coding. arXiv:1510.00149, 2016.
[19] Courbariaux M, Bengio Y, David JP. BinaryConnect: Training deep neural networks with binary weights during propagations. In: Proc.
of the 29th Int’l Conf. on Neural Information Processing Systems. Montreal: MIT Press, 2015. 3123–3131.
[20] Rastegari M, Ordonez V, Redmon J, Farhadi A. XNOR-Net: ImageNet classification using binary convolutional neural networks. In:
Proc. of the 14th European Conf. on Computer Vision. Amsterdam: Springer, 2016. 525–542. [doi: 10.1007/978-3-319-46493-0_32]
[21] Liu ZC, Wu BY, Luo WH, Yang X, Liu W, Cheng KT. Bi-Real net: Enhancing the performance of 1-bit CNNs with improved
representational capability and advanced training algorithm. In: Proc. of the 15th European Conf. on Computer Vision (ECCV). Munich:
Springer, 2018. 747–763. [doi: 10.1007/978-3-030-01267-0_44]
[22] Lin XF, Zhao C, Pan W. Towards accurate binary convolutional neural network. In: Proc. of the 31st Int’l Conf. on Neural Information
Processing Systems. Long Beach: Curran Associates Inc., 2017. 344–352.
[23] Zhu SL, Dong X, Su H. Binary ensemble neural network: More bits per network or more networks per bit? In: Proc. of the 2019
IEEE/CVF Conf. on Computer Vision and Pattern Recognition. Long Beach: IEEE, 2019. 4918–4927. [doi: 10.1109/CVPR.2019.00506]
[24] He YH, Zhang XY, Sun J. Channel pruning for accelerating very deep neural networks. In: Proc. of the 2017 IEEE Int’l Conf. on
Computer Vision. Venice: IEEE, 2017. 1398–1406. [doi: 10.1109/ICCV.2017.155]
[25] He Y, Kang GL, Dong XY, Fu YW, Yang Y. Soft filter pruning for accelerating deep convolutional neural networks. In: Proc. of the 27th
Int’l Joint Conf. on Artificial Intelligence. Stockholm: AAAI Press, 2018. 2234–2240. [doi: 10.24963/ijcai.2018/309]
[26] Liu Z, Li JG, Shen ZQ, Huang G, Yan SM, Zhang CS. Learning efficient convolutional networks through network slimming. In: Proc. of
the 2017 IEEE Int’l Conf. on Computer Vision. Venice: IEEE, 2017. 2755–2763. [doi: 10.1109/ICCV.2017.298]
[27] He Y, Liu P, Wang ZW, Hu ZL, Yang Y. Filter pruning via geometric median for deep convolutional neural networks acceleration. In:
Proc. of the 2019 IEEE/CVF Conf. on Computer Vision and Pattern Recognition. Long Beach: IEEE, 2019. 4335–4344. [doi: 10.1109/
CVPR.2019.00447]
[28] Tan MH, Gao WF, Li H, Xie J, Gong MG. Universal binary neural networks design by improved differentiable neural architecture search.
IEEE Trans. on Circuits and Systems for Video Technology, 2024, 34(10): 9153–9165. [doi: 10.1109/TCSVT.2024.3398691]
[29] Bulat A, Martinez B, Tzimiropoulos G. BATS: Binary architecture search. In: Proc. of the 16th European Conf. on Computer Vision.
Glasgow: Springer, 2020. 309–325. [doi: 10.1007/978-3-030-58592-1_19]
[30] Romero A, Ballas N, Kahou SE, Chassang A, Gatta C, Bengio Y. FitNets: Hints for thin deep nets. arXiv:1412.6550, 2015.
[31] Zagoruyko S, Komodakis N. Paying more attention to attention: Improving the performance of convolutional neural networks via
attention transfer. arXiv:1612.03928, 2017.
[32] Bengio Y, Léonard N, Courville A. Estimating or propagating gradients through stochastic neurons for conditional computation. arXiv:
1308.3432, 2013.