| DenseNet模型轻量化改进研究 |
| |
| 引用本文： | 舒军,蒋明威,杨莉,陈宇.DenseNet模型轻量化改进研究[J].华中师范大学学报(自然科学版),2020,54(2):187-193. |
| |
| 作者姓名： | 舒军 蒋明威 杨莉 陈宇 |
| |
| 作者单位： | 1.湖北工业大学电气与电子工程学院， 武汉 430068；2.湖北工业大学太阳能高效利用及储能运行控制湖北省重点实验室， 武汉 430068；3.湖北第二师范学院计算机学院， 武汉 430205 |
| |
| 摘 要： | 针对深层DenseNet模型在小型数据集上的过拟合问题，提出了一种改进的轻量化DenseNet模型.首先，优化网络中密集连接块(Dense Block)数量和其内部网络结构；然后，提出一种自适应池化层方法，解决改进网络的特征图分辨率适应问题；最后，加入Skip Layer模块增强密集连接块间特征信息流通.实验结果表明，改进方法能够减少模型的参数量和计算量，有效解决了深层DenseNet的过拟合问题.
|
| 关 键 词： | DenseNet Skip Layer 深度网络 模型轻量化 |
| 收稿时间： | 2020-05-19 |
Lightweight improvement research of DenseNet model |
| |
| SHU Jun,JIANG Mingwei,YANG Li,CHEN Yu.Lightweight improvement research of DenseNet model[J].Journal of Central China Normal University(Natural Sciences),2020,54(2):187-193. |
| |
| Authors: | SHU Jun JIANG Mingwei YANG Li CHEN Yu |
| |
| Institution: | 1.School of Electrical and Electronic Engineering， Hubei University of Technology，Wuhan 430068， China；2.Hubei Key Laboratory for High-efficiency Utilization of Solar Energy and Operation Control of Energy Storage System， Hubei University of Technology， Wuhan 430068， China；3.School of Computer， Hubei University of Education， Wuhan 430205， China |
| |
| Abstract: | Aiming at the overfitting problem of deep DenseNet model on small-scale data sets， an improved lightweight DenseNet model is proposed in this paper. Firstly， we optimized the number of DenseBlock and its internal network structure. Then， an adaptive pooling layer method is proposed to solve the problem of adapting the resolution of the feature map of the new network. Finally， we added the SkipLayer to enhance the flow of feature information between DenseBlocks. The experimental results illustrated that the new method can reduced the parameter and calculation amount of the model， and solve the over-fitting problem of deep DenseNet effectively . |
| |
| Keywords: | DenseNet Skip Layer deep Network model lightweight |
| 本文献已被 万方数据 等数据库收录！ |
| 点击此处可从《华中师范大学学报(自然科学版)》浏览原始摘要信息 |
| 点击此处可从《华中师范大学学报(自然科学版)》下载免费的PDF全文 |
