Abstract
Most binary networks apply full precision convolution at the first layer. Changing the first layer to the binary convolution will result in a significant loss of accuracy. In this paper, we propose a new approach to solve this problem by widening the data channel to reduce the information loss of the first convolutional input through the sign function. In addition, widening the channel increases the computation of the first convolution layer, and the problem is solved by using group convolution. The experimental results show that the accuracy of applying this paper’s method to state-of-the-art (SOTA) binarization method is significantly improved, proving that this paper’s method is effective and feasible.
This is a preview of subscription content, log in via an institution to check access.
Similar content being viewed by others
References
HE R, SUN S, YANG J, et al. Knowledge distillation as efficient pre-training: faster convergence, higher data-efficiency, and better transferability[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, June 19–24, 2022, New Orleans, Louisiana, USA. New York: IEEE, 2022: 9161–9171.
ZHANG L, CHEN X, TU X, et al. Wavelet knowledge distillation: towards efficient image-to-image translation[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, June 19–24, 2022, New Orleans, Louisiana, USA. New York: IEEE, 2022: 12464–12474.
ZHONG Y, LIN M, NAN G, et al. IntraQ: learning synthetic images with intra-class heterogeneity for zero-shot network quantization[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, June 19–24, 2022, New Orleans, Louisiana, USA. New York: IEEE, 2022: 12339–12348.
LIU C, DING W, XIA X, et al. Circulant binary convolutional networks: enhancing the performance of 1-bit DCNNs with circulant back propagation[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, June 13–19, 2019, Long Beach, CA, USA. New York: IEEE, 2019: 2691–2699.
LIU Z, SHEN Z, SAVVIDES M, et al. ReActNet: towards precise binary neural network with generalized activation functions[C]//European Conference on Computer Vision, August 23–28, 2020, Virtual. Cham: Springer, 2020: 143–159.
ZHOU S, WU Y, NI Z, et al. Dorefa-net: training low bit width convolutional neural networks with low bit width gradients[EB/OL]. (2016-06-20) [2022-06-22]. https://arxiv.org/pdf/1606.06160.pdf.
DING R, CHIN T W, LIU Z, et al. Regularizing activation distribution for training binarized deep networks[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, June 13–19, 2019, Long Beach, CA, USA. New York: IEEE, 2019: 11408–11417.
HOWARD A G, ZHU M, CHEN B, et al. Mobilenets: efficient convolutional neural networks for mobile vision applications[EB/OL]. (2017-04-17) [2022-06-22]. https://arxiv.org/pdf/1704.04861.pdf.
ZHANG X, ZHOU X, LIN M, et al. Shufflenet: an extremely efficient convolutional neural network for mobile devices[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, June 18–22, 2018, Salt Lake City, UT, USA. New York: IEEE, 2018: 6848–6856.
MEHTA S, RASTEGARI M. Mobilevit: light-weight, general-purpose, and mobile-friendly vision transformer[EB/OL]. (2021-10-17) [2022-06-22]. https://arxiv.org/pdf/2110.02178v2.pdf.
QIN H, GONG R, LIU X, et al. Forward and backward information retention for accurate binary neural networks[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, June 13–19, 2020, Seattle, WA, USA. New York: IEEE, 2020: 2250–2259.
LIU Z, WU B, LUO W, et al. Bi-real net: enhancing the performance of 1-bit CNNs with improved representational capability and advanced training algorithm[C]//Proceedings of the European Conference on Computer Vision, September 8–14, 2018, Munich, Germany. Berlin, Heidelberg: Springer-Verlag, 2018: 722–737.
LIN X, ZHAO C, PAN W. Towards accurate binary convolutional neural network[J]. Advances in neural information processing systems, 2017, 30: 345–353.
SU Z, FANG L, GUO D, et al. FTBNN: rethinking non-linearity for 1-bit CNNs and going beyond[EB/OL]. (2010-09-29) [2022-06-22]. https://www.xueshufan.com/reader/3096361616.
KIM H, KIM K, KIM J, et al. Binaryduo: reducing gradient mismatch in binary activation network by coupling binary activations[EB/OL]. (2002-06-05) [2022-06-22]. https://arxiv.org/pdf/2002.06517v1.pdf.
XIE S, GIRSHICK R, DOLLÁR P, et al. Aggregated residual transformations for deep neural networks[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, July 21–26, 2017, Honolulu, HI, USA. New York: IEEE, 2017: 1492–1500.
CHOLLET F. Xception: deep learning with depth wise separable convolutions[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, July 21–26, 2017, Honolulu, HI, USA. New York: IEEE, 2017: 1251–1258.
HUBARA I, COURBARIAUX M, SOUDRY D, et al. Binarized neural networks[J]. Advances in neural information processing systems, 2016, 29: 4107–4115.
GONG R, LIU X, JIANG S, et al. Differentiable soft quantization: bridging full-precision and low-bit neural networks[C]//Proceedings of the IEEE International Conference on Computer Vision, October 27-November 3, 2019, Seoul, South Korea. New York: IEEE, 2019: 4852–4861.
Author information
Authors and Affiliations
Corresponding author
Ethics declarations
The authors declare that there are no conflicts of interest related to this article.
Additional information
This work has been supported by the National Natural Science Foundation of China (No.62172229).
Rights and permissions
About this article
Cite this article
Zhang, Q., Sun, L., Yang, G. et al. TBNN: totally-binary neural network for image classification. Optoelectron. Lett. 19, 117–122 (2023). https://doi.org/10.1007/s11801-023-2113-2
Received:
Revised:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11801-023-2113-2