An improved model training method for residual convolutional neural networks in deep learning

Li Xuelei; Li Rengang; Zhao Yaqian; Zhao Jian

首页> 外文期刊>Multimedia Tools and Applications >An improved model training method for residual convolutional neural networks in deep learning

【24h】

An improved model training method for residual convolutional neural networks in deep learning

机译：深度学习中剩余卷积神经网络的改进模型训练方法

获取原文

获取原文并翻译 | 示例

掌桥外文数据库（机构版） >>

开具论文收录证明 >>

页面导航

摘要
著录项
相关主题

摘要

Residual convolutional neural network (R-CNN) has become a promising method for image recognition in deep learning applications. The application accuracy, as a key indicator, has a close relationship with filter weights in trained R-CNN models. In order to make filters work at full capacity, we find out that lower relevancy between filters in the same layer promotes higher accuracy for R-CNN applications. Furthermore, we propose an improved R-CNN model training method to acquire a higher accuracy and a better generalization ability. In this paper, the main focus is to control the update of filter weights during model training. The key mechanism is achieved through computing the relevancy between filters in the same layer. The relevancy is quantified by a correlation coefficient, e.g., Pearson Correlation Coefficient (PCC). The mechanism takes a larger probability to utilize the updated filter weights with a lower correlation coefficient, and vice versa. In order to validate our proposal, we construct an experiment through PCC on residual networks. The experiment demonstrates that the improved model training method is a promising mean with better generalization ability and higher recognition accuracy (0.52%-1.83%) for residual networks.

机译：残余卷积神经网络（R-CNN）已成为深度学习应用中的图像识别的有希望的方法。作为一个关键指示器的应用准确性与训练的R-CNN模型中的滤波器重量密切相关。为了使滤波器以满体工作，我们发现相同层中的过滤器之间的较低相关性促使R-CNN应用的更高精度。此外，我们提出了一种改进的R-CNN模型训练方法来获得更高的准确性和更好的泛化能力。在本文中，主要焦点是在模型训练期间控制滤波器权重的更新。通过计算同一层中的过滤器之间的相关性来实现关键机制。相关性通过相关系数，例如Pearson相关系数（PCC）量化。该机制采用更大的概率来利用具有较低相关系数的更新的滤波器权重，反之亦然。为了验证我们的提案，我们通过PCC对剩余网络进行实验。该实验表明，改进的模型训练方法是具有更好的泛化能力和更高的识别准确性（0.52％-1.83％）的承诺平均值。

著录项

来源
《Multimedia Tools and Applications》 |2021年第5期|6811-6821|共11页
作者
Li Xuelei; Li Rengang; Zhao Yaqian; Zhao Jian;
展开▼
作者单位

Inspur Beijing Elect Informat Ind Co Ltd Beijing 100876 Peoples R China;

Inspur Elect Informat Ind Co Ltd Jinan 250101 Peoples R China|State Key Lab High End Server & Storage Technol Jinan 250101 Peoples R China;

Inspur Elect Informat Ind Co Ltd Jinan 250101 Peoples R China|State Key Lab High End Server & Storage Technol Jinan 250101 Peoples R China;

Inspur Elect Informat Ind Co Ltd Jinan 250101 Peoples R China|State Key Lab High End Server & Storage Technol Jinan 250101 Peoples R China;

展开▼
收录信息
原文格式 PDF
正文语种 eng
中图分类
关键词
Image classification; Residual convolutional neural network; Deep learning; Artificial intelligence;

机译：图像分类;剩余卷积神经网络;深入学习;人工智能;

An improved model training method for residual convolutional neural networks in deep learning

摘要

著录项

相关主题

期刊订阅