Knowledge Commons of Institute of Automation,CAS
Sparsity-Inducing Binarized Neural Networks | |
Wang, Peisong1,2; He, Xiangyu1,2; Li, Gang1,2; Zhao, Tianli1,2; Cheng, Jian1,2 | |
2020 | |
会议名称 | AAAI |
会议日期 | 2020 |
会议地点 | New York |
摘要 | Binarization of feature representation is critical for Binarized Neural Networks (BNNs). Currently, sign function is the commonly used method for feature binarization. Although it works well on small datasets, the performance on ImageNet remains unsatisfied. Previous methods mainly focus on minimizing quantization error, improving the training strategies and decomposing each convolution layer into several binary convolution modules. However, whether sign is the only option for binarization has been largely overlooked. In this work, we propose the Sparsity-inducing Binarized Neural Network (Si-BNN), to quantize the activations to be either 0 or+ 1, which introduces sparsity into binary representation. We further introduce trainable thresholds into the backward function of binarization to guide the gradient propagation. Our method dramatically outperforms current state-ofthe-arts, lowering the performance gap between full-precision networks and BNNs on mainstream architectures, achieving the new state-of-the-art on binarized AlexNet (Top-1 50.5%), ResNet-18 (Top-1 59.7%), and VGG-Net (Top-1 63.2%). At inference time, Si-BNN still enjoys the high efficiency of exclusive-not-or (xnor) operations. |
收录类别 | EI |
七大方向——子方向分类 | AI芯片与智能计算 |
文献类型 | 会议论文 |
条目标识符 | http://ir.ia.ac.cn/handle/173211/40621 |
专题 | 复杂系统认知与决策实验室_高效智能计算与学习 紫东太初大模型研究中心_图像与视频分析 |
通讯作者 | Cheng, Jian |
作者单位 | 1.Institute of Automation, Chinese Academy of Sciences 2.University of Chinese Academy of Sciences |
第一作者单位 | 中国科学院自动化研究所 |
通讯作者单位 | 中国科学院自动化研究所 |
推荐引用方式 GB/T 7714 | Wang, Peisong,He, Xiangyu,Li, Gang,et al. Sparsity-Inducing Binarized Neural Networks[C],2020. |
条目包含的文件 | ||||||
文件名称/大小 | 文献类型 | 版本类型 | 开放类型 | 使用许可 | ||
6900-Article Text-10(578KB) | 会议论文 | 开放获取 | CC BY-NC-SA | 浏览 |
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。
修改评论