【推荐】卷积神经网络类间不平衡问题系统研究

2017 年 10 月 18 日 机器学习研究会
【推荐】卷积神经网络类间不平衡问题系统研究


点击上方 “机器学习研究会”可以订阅
摘要
 

转自:爱可可-爱生活

论文《A systematic study of the class imbalance problem in convolutional neural networks》摘要:

In this study, we systematically investigate the impact of class imbalance on classification performance of convolutional neural networks (CNNs) and compare frequently used methods to address the issue. Class imbalance is a common problem that has been comprehensively studied in classical machine learning, yet very limited systematic research is available in the context of deep learning. In our study, we use three benchmark datasets of increasing complexity, MNIST, CIFAR-10 and ImageNet, to investigate the effects of imbalance on classification and perform an extensive comparison of several methods to address the issue: oversampling, undersampling, two-phase training, and thresholding that compensates for prior class probabilities. Our main evaluation metric is area under the receiver operating characteristic curve (ROC AUC) adjusted to multi-class tasks since overall accuracy metric is associated with notable difficulties in the context of imbalanced data. Based on results from our experiments we conclude that (i) the effect of class imbalance on classification performance is detrimental; (ii) the method of addressing class imbalance that emerged as dominant in almost all analyzed scenarios was oversampling; (iii) oversampling should be applied to the level that totally eliminates the imbalance, whereas undersampling can perform better when the imbalance is only removed to some extent; (iv) as opposed to some classical machine learning models, oversampling does not necessarily cause overfitting of CNNs; (v) thresholding should be applied to compensate for prior class probabilities when overall number of properly classified cases is of interest.


链接:

https://arxiv.org/abs/1710.05381


原文链接:

https://m.weibo.cn/1402400261/4164068987815246

“完整内容”请点击【阅读原文】
↓↓↓
登录查看更多
6

相关内容

在深度学习中,卷积神经网络(CNN或ConvNet)是一类深度神经网络,最常用于分析视觉图像。基于它们的共享权重架构和平移不变性特征,它们也被称为位移不变或空间不变的人工神经网络(SIANN)。它们在图像和视频识别,推荐系统,图像分类,医学图像分析,自然语言处理,和财务时间序列中都有应用。

知识荟萃

精品入门和进阶教程、论文和代码整理等

更多

查看相关VIP内容、论文、资讯等

A key component to the success of deep learning is the availability of massive amounts of training data. Building and annotating large datasets for solving medical image classification problems is today a bottleneck for many applications. Recently, capsule networks were proposed to deal with shortcomings of Convolutional Neural Networks (ConvNets). In this work, we compare the behavior of capsule networks against ConvNets under typical datasets constraints of medical image analysis, namely, small amounts of annotated data and class-imbalance. We evaluate our experiments on MNIST, Fashion-MNIST and medical (histological and retina images) publicly available datasets. Our results suggest that capsule networks can be trained with less amount of data for the same or better performance and are more robust to an imbalanced class distribution, which makes our approach very promising for the medical imaging community.

0
3
下载
预览
小贴士
相关资讯
(TensorFlow)实时语义分割比较研究
机器学习研究会
9+阅读 · 2018年3月12日
【推荐】深度学习情感分析综述
机器学习研究会
51+阅读 · 2018年1月26日
【干货】机器学习中样本比例不平衡的处理方法
机器学习研究会
8+阅读 · 2018年1月14日
【推荐】YOLO实时目标检测(6fps)
机器学习研究会
17+阅读 · 2017年11月5日
【推荐】决策树/随机森林深入解析
机器学习研究会
5+阅读 · 2017年9月21日
【推荐】深度学习目标检测全面综述
机器学习研究会
17+阅读 · 2017年9月13日
【推荐】GAN架构入门综述(资源汇总)
机器学习研究会
9+阅读 · 2017年9月3日
【推荐】深度学习目标检测概览
机器学习研究会
9+阅读 · 2017年9月1日
【推荐】SVM实例教程
机器学习研究会
15+阅读 · 2017年8月26日
相关VIP内容
专知会员服务
41+阅读 · 2020年3月19日
专知会员服务
46+阅读 · 2020年3月16日
专知会员服务
101+阅读 · 2020年2月1日
强化学习最新教程,17页pdf
专知会员服务
70+阅读 · 2019年10月11日
机器学习入门的经验与建议
专知会员服务
45+阅读 · 2019年10月10日
【哈佛大学商学院课程Fall 2019】机器学习可解释性
专知会员服务
54+阅读 · 2019年10月9日
相关论文
1D Convolutional Neural Networks and Applications: A Survey
Serkan Kiranyaz,Onur Avci,Osama Abdeljaber,Turker Ince,Moncef Gabbouj,Daniel J. Inman
4+阅读 · 2019年5月9日
Yu Cheng,Mo Yu,Xiaoxiao Guo,Bowen Zhou
11+阅读 · 2019年1月26日
Multi-class Classification without Multi-class Labels
Yen-Chang Hsu,Zhaoyang Lv,Joel Schlosser,Phillip Odom,Zsolt Kira
4+阅读 · 2019年1月2日
Thomas Elsken,Jan Hendrik Metzen,Frank Hutter
10+阅读 · 2018年9月5日
Fast and Accurate, Convolutional Neural Network Based Approach for Object Detection from UAV
Xiaoliang Wang,Peng Cheng,Xinchuan Liu,Benedict Uzochukwu
5+阅读 · 2018年8月16日
Andreas Kamilaris,Francesc X. Prenafeta-Boldu
9+阅读 · 2018年7月31日
Capsule Networks against Medical Imaging Data Challenges
Amelia Jiménez-Sánchez,Shadi Albarqouni,Diana Mateus
3+阅读 · 2018年7月19日
Marcelo Criscuolo,Erick Rocha Fonseca,Sandra Maria Aluísio,Ana Carolina Sperança-Criscuolo
4+阅读 · 2018年1月10日
Ke Zhang,Liru Guo,Ce Gao,Zhenbing Zhao
3+阅读 · 2017年10月1日
Top