From Hashing to CNNs: Training BinaryWeight Networks via Hashing
文献类型:会议论文
作者 | Hu, Qinghao1,2; Wang, Peisong1,2; Cheng, Jian1,2,3 |
出版日期 | 2018-02 |
会议日期 | 2018年2月2-8日 |
会议地点 | 美国新奥尔良 |
关键词 | Hashing Binary Weight Network Cnns |
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 real-world 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. |
源URL | [http://ir.ia.ac.cn/handle/173211/23703] |
专题 | 自动化研究所_模式识别国家重点实验室_图像与视频分析团队 |
通讯作者 | Cheng, Jian |
作者单位 | 1.Institute of Automation, Chinese Academy of Sciences, Beijing, China 2.University of Chinese Academy of Sciences, Beijing, China 3.Center for Excellence in Brain Science and Intelligence Technology, CAS, Beijing, China |
推荐引用方式 GB/T 7714 | Hu, Qinghao,Wang, Peisong,Cheng, Jian. From Hashing to CNNs: Training BinaryWeight Networks via Hashing[C]. 见:. 美国新奥尔良. 2018年2月2-8日. |
入库方式: OAI收割
来源:自动化研究所
其他版本
除非特别说明,本系统中所有内容都受版权保护,并保留所有权利。