.png){kind=icon}
返回
VecQ: Minimal Loss DNN Model Compression With Vectorized Weight Quantization
.png){kind=icon}
OA
AI
DOI：10.1109/TC.2020.2995593.png)
.png){kind=icon}
.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
Quantization has been proven to be an effective method for reducing the computing and/or storage cost of DNNs. However, the trade-off between the quantization bitwidth and final accuracy is complex and non-convex, which makes it difficult to be optimized directly. Minimizing direct quantization loss (DQL) of the coefficient data is an effective local optimization method, but previous works often neglect the accurate control of the DQL, resulting in a higher loss of the final DNN model accuracy. In this paper, we propose a novel metric, called Vector Loss. Using this new metric, we decompose the minimization of the DQL to two independent optimization processes, which significantly outperform the traditional iterative L2 loss minimization process in terms of effectiveness, quantization loss as well as final DNN accuracy. We also develop a new DNN quantization solution called VecQ, which provides minimal direct quantization loss and achieve higher model accuracy. In order to speed up the proposed quantization process during model training, we accelerate the quantization process with a parameterized probability estimation method and template-based derivation calculation. We evaluate our proposed algorithm on MNIST, CIFAR, ImageNet, IMDB movie review and THUCNews text data sets with numerical DNN models. The results demonstrate that our proposed quantization solution is more accurate and effective than the state-of-the-art approaches yet with more flexible bitwidth support. Moreover, the evaluation of our quantized models on Salient Object Detection (SOD) tasks maintains comparable feature extraction quality with up to 16x weight size reduction.
Keyword:
Quantization (signal)
Training
Euclidean distance
Computational modeling
Data models
Numerical models
DNN compression
DNN quantization
vectorized weight quantization
low bitwidth
vector loss
AI总结
对已上传原文的论文进行重点信息的提取，主要内容包括：简要概述、研究摘要、背景介绍、关键亮点、图文解析、展望与总结。
期刊
IF:
3.8
论文数:
5.3K
被引数:
9.8K
机构
引用论文
Thermal comfort, perceived air quality, and cognitive performance when personally controlled air movement is used by tropically acclimatized persons当热带适应的人使用个人控制的空气运动时，热舒适性，感知的空气质量和认知表现.png)
Indoor AirOAAI
Indoor AirIF0
OAAI分享收藏Do Perceptions of Competence Mediate The Relationship Between Fundamental Motor Skill Proficiency and Physical Activity Levels of Children in Kindergarten?能力的感知是否可以介导幼儿园儿童的基本运动技能熟练程度与身体活动水平之间的关系？
PREAI
分享收藏
The power of obfuscation techniques in malicious JavaScript code: A measurement study恶意JavaScript代码中混淆技术的功能: 一项测量研究OAAI
OAAI分享收藏GXNOR-Net: Training deep neural networks with ternary weights and activations without full-precision memory under a unified discretization frameworkNEURAL NETWORKSOAAI
NEURAL NETWORKSIF6.3
OAAI分享收藏
查看更多内容