二值化網(wǎng)絡(luò)如何訓(xùn)練?這篇ICML 2021論文給你答案
這篇來(lái)自 CMU 和 HKUST 科研團(tuán)隊(duì)的 ICML 論文,僅通過(guò)調(diào)整訓(xùn)練算法,在 ImageNet 數(shù)據(jù)集上取得了比之前的 SOTA BNN 網(wǎng)絡(luò) ReActNet 高1.1% 的分類(lèi)精度。



論文地址:https://arxiv.org/abs/2106.11309
代碼地址:https://github.com/liuzechun/AdamBNN













Helwegen, K., Widdicombe, J., Geiger, L., Liu, Z., Cheng, K.-T., and Nusselder, R. Latent weights do not exist: Rethinking binarized neural network optimization. In Advances in neural information processing systems, pp. 7531–7542, 2019.
Liu, Z., Wu, B., Luo, W., Yang, X., Liu, W., and Cheng, K.- T. 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 (ECCV), pp. 722–737, 2018b.
Liu, Z., Shen, Z., Savvides, M., and Cheng, K.-T. Reactnet: Towards precise binary neural network with generalized activation functions. ECCV, 2020.
Brais Martinez, Jing Yang, A. B. G. T. Training binary neural networks with real-to-binary convolutions. Inter- national Conference on Learning Representations, 2020.
? THE END
轉(zhuǎn)載請(qǐng)聯(lián)系機(jī)器之心公眾號(hào)獲得授權(quán)
投稿或?qū)で髨?bào)道:[email protected]

點(diǎn)個(gè)在看 paper不斷!
