Self-Paced Balance Learning for Clinical Skin Disease Recognition

doi:10.1109/TNNLS.2019.2917524

CASIA OpenIR > 智能感知与计算研究中心

	Self-Paced Balance Learning for Clinical Skin Disease Recognition
	Yang, Jufeng 1; Wu, Xiaoping 1; Liang, Jie 1; Sun, Xiaoxiao 1; Cheng, Ming-Ming 1; Rosin, Paul L.2; Wang, Liang3
发表期刊	IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS
ISSN	2162-237X
	2020-08-01
卷号	31 期号:8 页码:2832-2846
通讯作者	Yang, Jufeng(yangjufeng@nankai.edu.cn)
摘要	Class imbalance is a challenging problem in many classification tasks. It induces biased classification results for minority classes that contain less training samples than others. Most existing approaches aim to remedy the imbalanced number of instances among categories by resampling the majority and minority classes accordingly. However, the imbalanced level of difficulty of recognizing different categories is also crucial, especially for distinguishing samples with many classes. For example, in the task of clinical skin disease recognition, several rare diseases have a small number of training samples, but they are easy to diagnose because of their distinct visual properties. On the other hand, some common skin diseases, e.g., eczema, are hard to recognize due to the lack of special symptoms. To address this problem, we propose a self-paced balance learning (SPBL) algorithm in this paper. Specifically, we introduce a comprehensive metric termed the complexity of image category that is a combination of both sample number and recognition difficulty. First, the complexity is initialized using the model of the first pace, where the pace indicates one iteration in the self-paced learning paradigm. We then assign each class a penalty weight that is larger for more complex categories and smaller for easier ones, after which the curriculum is reconstructed by rearranging the training samples. Consequently, the model can iteratively learn discriminative representations via balancing the complexity in each pace. Experimental results on the SD-198 and SD-260 benchmark data sets demonstrate that the proposed SPBL algorithm performs favorably against the state-of-the-art methods. We also demonstrate the effectiveness of the SPBL algorithm's generalization capacity on various tasks, such as indoor scene image recognition and object classification.
关键词	Diseases Skin Complexity theory Training Task analysis Image recognition Learning systems Class imbalance clinical skin disease recognition complexity level self-paced balance learning (SPBL)
DOI	10.1109/TNNLS.2019.2917524
关键词[WOS]	CONVOLUTIONAL NEURAL-NETWORKS ; SUPPORT VECTOR MACHINES ; CLASSIFICATION ; SMOTE ; RULE
收录类别	SCI
语种	英语
资助项目	NSFC[61876094] ; Natural Science Foundation of Tianjin, China[18JCYBJC15400] ; Natural Science Foundation of Tianjin, China[18ZXZNGX00110] ; Open Project Program of the National Laboratory of Pattern Recognition (NLPR) ; Fundamental Research Funds for the Central Universities
项目资助者	NSFC ; Natural Science Foundation of Tianjin, China ; Open Project Program of the National Laboratory of Pattern Recognition (NLPR) ; Fundamental Research Funds for the Central Universities
WOS研究方向	Computer Science ; Engineering
WOS类目	Computer Science, Artificial Intelligence ; Computer Science, Hardware & Architecture ; Computer Science, Theory & Methods ; Engineering, Electrical & Electronic
WOS记录号	WOS:000557365700013
出版者	IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
引用统计	被引频次：38[WOS] [WOS记录] [WOS相关记录]
文献类型	期刊论文
条目标识符	http://ir.ia.ac.cn/handle/173211/40353
专题	智能感知与计算研究中心
通讯作者	Yang, Jufeng
作者单位	1.Nankai Univ, Coll Comp Sci, Tianjin 300350, Peoples R China 2.Cardiff Univ, Sch Comp Sci & Informat, Cardiff CF10 3AT, Wales 3.Chinese Acad Sci, Inst Automat, CAS Ctr Excellence Brain Sci & Intelligence Techn, Natl Lab Pattern Recognit, Beijing 100190, Peoples R China
推荐引用方式 GB/T 7714	Yang, Jufeng,Wu, Xiaoping,Liang, Jie,et al. Self-Paced Balance Learning for Clinical Skin Disease Recognition[J]. IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS,2020,31(8):2832-2846.
APA	Yang, Jufeng.,Wu, Xiaoping.,Liang, Jie.,Sun, Xiaoxiao.,Cheng, Ming-Ming.,...&Wang, Liang.(2020).Self-Paced Balance Learning for Clinical Skin Disease Recognition.IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS,31(8),2832-2846.
MLA	Yang, Jufeng,et al."Self-Paced Balance Learning for Clinical Skin Disease Recognition".IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS 31.8(2020):2832-2846.