Knowledge Commons of Institute of Automation,CAS
Dual-discriminator adversarial framework for data-free quantization | |
Li, Zhikai1,2; Ma, Liping1; Long, Xianlei1,2; Xiao, Junrui1,2; Gu, Qingyi1 | |
发表期刊 | NEUROCOMPUTING |
ISSN | 0925-2312 |
2022-10-28 | |
卷号 | 511页码:67-77 |
摘要 | Thanks to the potential to address the privacy and security issues, data-free quantization that generates samples based on the prior information in the model has recently been widely investigated. However, existing methods failed to adequately utilize the prior information and thus cannot fully restore the real-data characteristics and provide effective supervision to the quantized model, resulting in poor performance. In this paper, we propose Dual-Discriminator Adversarial Quantization (DDAQ), a novel data-free quantization framework with an adversarial learning style that enables effective sample generation and learning of the quantized model. Specifically, we employ a generator to produce meaningful and diverse samples directed by two discriminators, aiming to facilitate the matching of the batch normalization (BN) distribution and maximizing the discrepancy between the full-precision model and the quantized model, respectively. Moreover, inspired by mixed-precision quantization, i.e., the importance of each layer is different, we introduce layer importance prior to both discriminators, allowing us to make better use of the information in the model. Subsequently, the quantized model is trained with the generated samples under the supervision of the full-precision model. We evaluate DDAQ on various network structures for different vision tasks, including image classification and object detection, and the experimental results show that DDAQ outperforms all baseline methods with good generality. (C) 2022 Elsevier B.V. All rights reserved. |
其他摘要 |
|
关键词 | Model compression Quantized neural networks Data-free quantization |
DOI | 10.1016/j.neucom.2022.09.076 |
收录类别 | SCI |
语种 | 英语 |
资助项目 | Scientific Instrument Developing Project of the Chinese Academy of Sciences[YJKYYQ20200045] |
项目资助者 | Scientific Instrument Developing Project of the Chinese Academy of Sciences |
WOS研究方向 | Computer Science |
WOS类目 | Computer Science, Artificial Intelligence |
WOS记录号 | WOS:000871948700006 |
出版者 | ELSEVIER |
七大方向——子方向分类 | 机器学习 |
国重实验室规划方向分类 | 环境多维感知 |
引用统计 | |
文献类型 | 期刊论文 |
条目标识符 | http://ir.ia.ac.cn/handle/173211/50524 |
专题 | 中科院工业视觉智能装备工程实验室_精密感知与控制 |
通讯作者 | Gu, Qingyi |
作者单位 | 1.Chinese Acad Sci, Inst Automat, East Zhongguancun Rd, Beijing, Peoples R China 2.Univ Chinese Acad Sci, Sch Artificial Intelligence, Jingjia Rd, Beijing, Peoples R China |
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 | Li, Zhikai,Ma, Liping,Long, Xianlei,et al. Dual-discriminator adversarial framework for data-free quantization[J]. NEUROCOMPUTING,2022,511:67-77. |
APA | Li, Zhikai,Ma, Liping,Long, Xianlei,Xiao, Junrui,&Gu, Qingyi.(2022).Dual-discriminator adversarial framework for data-free quantization.NEUROCOMPUTING,511,67-77. |
MLA | Li, Zhikai,et al."Dual-discriminator adversarial framework for data-free quantization".NEUROCOMPUTING 511(2022):67-77. |
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 | ||
1-s2.0-S092523122201(1512KB) | 期刊论文 | 作者接受稿 | 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