Unimodal regularized neuron stick-breaking for ordinal classification
X. F. Liu; F. F. Fan; L. S. Kong; Z. H. Diao; W. Q. Xie; J. Lu and J. N. You
刊名Neurocomputing
2020
卷号388页码:34-44
ISSN号0925-2312
DOI10.1016/j.neucom.2020.01.025
英文摘要This paper targets for the ordinal regression/classification, which objective is to learn a rule to predict labels from a discrete but ordered set. For instance, the classification for medical diagnosis usually involves inherently ordered labels corresponding to the level of health risk. Previous multi-task classifiers on ordinal data often use several binary classification branches to compute a series of cumulative probabilities. However, these cumulative probabilities are not guaranteed to be monotonically decreasing. It also introduces a large number of hyper-parameters to be fine-tuned manually. This paper aims to eliminate or at least largely reduce the effects of those problems. We propose a simple yet efficient way to rephrase the output layer of the conventional deep neural network. Besides, in order to alleviate the effects of label noise in ordinal datasets, we propose a unimodal label regularization strategy. It also explicitly encourages the class predictions to distribute on nearby classes of ground truth. We show that our methods lead to the state-of-the-art accuracy on the medical diagnose task (e.g., Diabetic Retinopathy and Ultrasound Breast dataset) as well as the face age prediction (e.g., Adience face and MORPH Album II) with very little additional cost. (C) 2020 Elsevier B.V. All rights reserved.
URL标识查看原文
语种英语
内容类型期刊论文
源URL[http://ir.ciomp.ac.cn/handle/181722/64994]  
专题中国科学院长春光学精密机械与物理研究所
推荐引用方式
GB/T 7714
X. F. Liu,F. F. Fan,L. S. Kong,et al. Unimodal regularized neuron stick-breaking for ordinal classification[J]. Neurocomputing,2020,388:34-44.
APA X. F. Liu,F. F. Fan,L. S. Kong,Z. H. Diao,W. Q. Xie,&J. Lu and J. N. You.(2020).Unimodal regularized neuron stick-breaking for ordinal classification.Neurocomputing,388,34-44.
MLA X. F. Liu,et al."Unimodal regularized neuron stick-breaking for ordinal classification".Neurocomputing 388(2020):34-44.
个性服务
查看访问统计
相关权益政策
暂无数据
收藏/分享
所有评论 (0)
暂无评论
 

除非特别说明,本系统中所有内容都受版权保护,并保留所有权利。


©版权所有 ©2017 CSpace - Powered by CSpace