arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1802.02733cs.CV
收藏

从哈希到CNN:通过哈希训练BinaryWeight网络

From Hashing to CNNs: Training BinaryWeight Networks via Hashing

Institute of Automation, Chinese Academy of Sciences(中国科学院自动化研究所);University of Chinese Academy of Sciences(中国科学院大学);Center for Excellence in Brain Science and Intelligence Technology, CAS(中国科学院脑科学与智能技术卓越创新中心)

Qinghao Hu, Peisong Wang, Jian Cheng

摘要:

近年来,深度卷积神经网络(CNN)在各种计算机视觉任务上表现出了吸引人的性能。这促使人们将CNN部署到现实世界的应用中。然而,大多数最先进的CNN需要大量的内存和计算资源,这阻碍了在移动设备上的部署。近年来的研究表明,低位权值表示可以减少大量的存储和内存需求,并且可以实现高效的网络推理。为了实现这一目标,我们提出了一种新的方法命名为BWNH通过哈希训练二进制权重网络。在本文中,我们首先揭示了内积保持哈希和二进制权重网络之间的紧密联系,并表明训练二进制权重网络本质上可以被视为哈希问题。基于这一观点,我们提出了一种交替优化方法来学习哈希码,而不是直接学习二进制权重。在CIFAR10、CIFAR100和ImageNet上的大量实验表明,我们提出的BWNH大大优于当前最先进的算法。

英文摘要:

Deep convolutional neural networks (CNNs) have shown appealing performance on various computer vision tasks in recent years. This motivates people to deploy CNNs to realworld applications. However, most of state-of-art CNNs require large memory and computational resources, which hinders the deployment on mobile devices. Recent studies show that low-bit weight representation can reduce much storage and memory demand, and also can achieve efficient network inference. To achieve this goal, we propose a novel approach named BWNH to train Binary Weight Networks via Hashing. In this paper, we first reveal the strong connection between inner-product preserving hashing and binary weight networks, and show that training binary weight networks can be intrinsically regarded as a hashing problem. Based on this perspective, we propose an alternating optimization method to learn the hash codes instead of directly learning binary weights. Extensive experiments on CIFAR10, CIFAR100 and ImageNet demonstrate that our proposed BWNH outperforms current state-of-art by a large margin.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑