arrow
返回

Sequence-Dropout Block for Reducing Overfitting Problem in Image Classification

delete2020-01-01
delete32
delete
OA
AI
L
Ledan Qian
L
Libing Hu *
L
Li Zhao *
T
Tao Wang
蒋润花 封面图
蒋润花 (Runhua Jiang)
DOI:10.1109/ACCESS.2020.2983774delete
delete原文链接
delete分享
delete收藏
查看原文
摘要

摘要

En 中文
Overfitting is a common problem for computer vision applications It is a problem that when training convolution neural networks and is caused by lack of training data or network complexity. The novel sequence-dropout (SD) method is proposed in this paper to alleviate the problem of overfitting when training networks. The SD method works by dropping out units (channels of feature) from the network in a sequence, replacing the traditional operation of random omitting. Sophisticated aggregation strategies are used to obtain the global information of feature channels, and channel-wise weights are produced by gating mechanism. The SD method then selectively drops out the feature channels according to the channel-wise weights that represent the importance degree of each channel. The proposed SD block can be plugged into state-of-the-art backbone CNN models such as VGGNet and ResNet. The SD block is then evaluated on these models, demonstrating consistent performance gains over the baseline model on widely-used benchmark image classification datasets including MNIST, CIFAR-10, CIFAR-100, and ImageNet2012. Experimental results demonstrate that the superior performance of the SD block compared to other modern methods.
Keyword:
Training
Convolution
Neural networks
Computer architecture
Computer vision
Training data
Task analysis
Convolutional networks
image classification
overfitting
sequence-dropout
AI总结

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

IEEE Access 封面图
IEEE Access
IF:
3.6
论文数:
9.8W
被引数:
29.4W

机构

W
Wenzhou University
学者数:
8.8K
论文数: 6.5K
被引数: 1.5W
引用论文

引用论文

510–515 nm InGaN-Based Green Laser Diodes onc-Plane GaN Substrate
err2009-05-22
err0
PREAI
errTakashi Miyoshi; Shingo Masui; Takeshi Okada; Tomoya Yanamoto; Tokuya Kozaki; Shin-ichi Nagahama; Takashi Mukai
err分享
err收藏
Psychosocial impact of illness intrusiveness moderated by self-concept and age in end-stage renal disease.
err1997-01-01
err0
PREAI
errGerald M. Devins; Heather Beanlands; Henry Mandin; Leendert C. Paul
err分享
err收藏
PTX encapsulated by an XG–DOX conjugate for combination therapy against multi-drug resistance
err2016-01-01
err0
PREAI
errZhuli Huang; Xuan Xie; Jean Felix Mukerabigwi; Chang Wang; Shufang Wang; Wang Xiao; Xueying Huang; Yu Cao
err分享
err收藏
err分享
err收藏
Bagging predictorsBagging预测器
err1996-08-01
err1.0W
PREAI
errBreiman, L
err分享
err收藏
学者 查看更多内容