Knowledge Commons of Institute of Automation,CAS
Towards Binarized MobileNet via Structured Sparsity | |
Zhenmeng, Zuo1; Zhexin, Li1,2; Peisong, Wang2; Weihan, Chen1,2; Jian, Cheng1,2 | |
2021-09-30 | |
会议名称 | International Conference on Image and Graphics, ICIG 2021 |
会议日期 | 2021-12-26 |
会议地点 | Hainan, China |
摘要 | The rising demand for deploying convolutional neural networks (CNNs) to mobile applications has promoted the booming of compact networks. Two parallel mainstream techniques include network compression and lightweight architecture design. Despite these two techniques can theoretically work together, the naive combination results in dramatic accuracy degradation. In this paper, we present Binarized MobileNet-Sp for mobile applications, by compression-architecture co-design. We first reveal the connection between MobileNets and low-rank decomposition, showing that decomposition-based architecture is not quantization friendly. Then, by adopting the view of sparsity, we propose the Binarized MobileNet-Sp, which significantly enhances the robustness to binarization. Experiments on ImageNet show that the proposed Binarized MobileNet-Sp achieves 61.2% top-1 accuracy, outperforming the naive binarization method by about 10% higher top-1 accuracy. Compared to the Bi-Real net which achieves 56.4% top-1 accuracy on the more heavy-weight and redundant ResNet-18 (which has comparable baseline accuracy with MobileNet in full-precision representation), the Binarized MobileNet-Sp achieves much higher accuracy with a significant reduction in computing complexity. |
DOI | https://doi.org/10.1007/978-3-030-87355-4_57 |
语种 | 英语 |
引用统计 | |
文献类型 | 会议论文 |
条目标识符 | http://ir.ia.ac.cn/handle/173211/48704 |
专题 | 复杂系统认知与决策实验室_高效智能计算与学习 |
通讯作者 | Jian, Cheng |
作者单位 | 1.University of Chinese Academy of Sciences, Beijing, China 2.NLPR, Institute of Automation, Chinese Academy of Sciences, Beijing, China |
通讯作者单位 | 模式识别国家重点实验室 |
推荐引用方式 GB/T 7714 | Zhenmeng, Zuo,Zhexin, Li,Peisong, Wang,et al. Towards Binarized MobileNet via Structured Sparsity[C],2021. |
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 | ||
Zuo2021_Chapter_Towa(476KB) | 会议论文 | 开放获取 | CC BY-NC-SA | 浏览 下载 |
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