Imbalanced multi-label image classification has gained increasing attention recently, in which each sample has multiple class labels, but the number of each category is unevenly distributed. It’s common in practical applications but traditional multi-label learning methods can hardly deal with imbalance problems. In this paper, we propose an effective method to tackle imbalanced multi-label learning. The class-aware embedding network is proposed to learn robust class-based representation. Additionally, by using the distribution-balanced loss to weigh different samples, our model can improve the feature learning ability of minority classes. Extensive experiments on widely used long-tailed manual multi-label datasets like VOC-LT and COCO-LT explicitly validate the proposed good method.


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    Class-aware Learning for Imbalanced Multi-Label Classification


    Contributors:
    Chen, Jiayao (author) / Li, Shaoyuan (author)


    Publication date :

    2023-10-11


    Size :

    2594740 byte




    Type of media :

    Conference paper


    Type of material :

    Electronic Resource


    Language :

    English



    Evaluation of Two Systems on Multi-class Multi-label Document Classification

    Luo, X. / Zincir-Heywood, A. N. | British Library Conference Proceedings | 2005




    Label Erasure Using an Imbalanced NOLM and Its Application in a 40-Gb/s Label Switching Optical Network

    Yu, J. / Chang, G.-K. / Akanbi, O. | British Library Online Contents | 2006