在BONN中,BONN遵循XNOR-Net采用的策略,该策略在第一个卷积层,所有1×1卷积和全连接层中保持全精度参数,由此,ResNet18的总体压缩率为11.10。对于效率分析,如果卷积的所有操作数都是二进制的,可以通过XNOR和位计数操作来估计卷积【M. Courbariaux, I. Hubara, D. Soudry, R. El-Yaniv, and Y. Bengio. Binarized neural networks: Training deep neural networks with weights and activations constrained to+ 1 or- 1. arXiv preprint arXiv:1602.02830, 2016】。
总结
作者提出了贝叶斯优化的1-bit CNNs(BONN),该模型考虑了全精度kernel和features分布,从而形成了具有两个新贝叶斯损失的统一贝叶斯框架。贝叶斯损失用于调整kernel和features的分布,以达到最佳解决方案。
参考文献【1】S. Zhou, Y. Wu, Z. Ni, X. Zhou, H. Wen, and Y. Zou. Dorefa-net: Training low bitwidth convolutional neural networks with low bitwidth gradients. arXiv preprint arXiv:1606.06160, 2016.【2】X. Lin, C. Zhao, and W. Pan. Towards accurate binary convolutional neural network. In Advances in Neural Information Processing Systems, pages 345–353, 2017.【3】X. Wang, B. Zhang, C. Li, R. Ji, J. Han, X. Cao, and J. Liu. Modulated convolutional networks. In IEEE Conference on Computer Vision and Pattern Recognition, pages 840–848, 2018.【4】C. Leng, Z. Dou, H. Li, S. Zhu, and R. Jin. Extremely low bit neural network: Squeeze the last bit out with admm. In AAAI Conference on Artificial Intelligence, 2018.【5】Z. Liu, B. Wu, W. Luo, X. Yang, W. Liu, and K.-T. Cheng. Bi-real net: Enhancing the performance of 1-bit cnns with improved representational capability and advanced training algorithm. In Proceedings of the European Conference on Computer Vision, pages 747–763. Springer, 2018.【6】B. Zhuang, C. Shen, M. Tan, L. Liu, and I. Reid. Towards effective low-bitwidth convolutional neural networks. In IEEE Conference on Computer Vision and Pattern Recognition, June 2018.【7】S. Wu, G. Li, F. Chen, and L. Shi. Training and inference with integers in deep neural networks. In International Conference on Learning Representations, 2018.【8】J. Gu, C. Li, B. Zhang, J. Han, X. Cao, J. Liu, and D. Doermann. Projection convolutional neural networks for 1-bit cnns via discrete back propagation. In AAAI Conference on Artificial Intelligence, 2019.【9】C. Blundell, J. Cornebise, K. Kavukcuoglu, and D. Wierstra. Weight uncertainty in neural network. In International Conference on Machine Learning, pages 1613–1622, 2015.