Multi-Label Image Classification with Weak Correlation Prior

作     者：Xiao Ouyang Ruidong Fan Hong Tao Chenping Hou 

作者机构：Department of Systems ScienceNational University of Defense TechnologyChangsha 410073China 

出 版 物：《CAAI Artificial Intelligence Research》 (CAAI人工智能研究（英文）)

年 卷 期：2022年第1卷第1期

页      面：79-92页

学科分类：08[工学] 0812[工学-计算机科学与技术（可授工学、理学学位）] 

基　　金：supported by the National Natural Science Foundation of China(Nos.61922087,61906201,62006238,and 62136005) the Natural Science Fund for Distinguished Young Scholars of Hunan Province(No.2019JJ20020). 

主　　题：image recognition label correlation multi-label classification weakly-supervised learning 

摘      要：Image classification is vital and basic in many data analysis domains.Since real-world images generally contain multiple diverse semantic labels,it amounts to a typical multi-label classification problem.Traditional multi-label image classification relies on a large amount of training data with plenty of labels,which requires a lot of human and financial costs.By contrast,one can easily obtain a correlation matrix of concerned categories in current scene based on the historical image data in other application scenarios.How to perform image classification with only label correlation priors,without specific and costly annotated labels,is an important but rarely studied problem.In this paper,we propose a model to classify images with this kind of weak correlation prior.We use label correlation to recapitulate the sample similarity,employ the prior information to decompose the projection matrix when regressing the label indication matrix,and introduce the L_(2,1) norm to select features for each image.Finally,experimental results on several image datasets demonstrate that the proposed model has distinct advantages over current state-of-the-art multi-label classification methods.