Existing class-incremental lifelong learning studies only the data is with single-label, which limits its adaptation to multi-label data. This paper studies Lifelong Multi-Label (LML) classification, which builds an online class-incremental classifier in a sequential multi-label classification data stream. Training on the data with Partial Labels in LML classification may result in more serious Catastrophic Forgetting in old classes. To solve the problem, the study proposes an Augmented Graph Convolutional Network (AGCN) with a built Augmented Correlation Matrix (ACM) across sequential partial-label tasks. The results of two benchmarks show that the method is effective for LML classification and reducing forgetting.
@article{arxiv.2207.07840,
title = {Class-Incremental Lifelong Learning in Multi-Label Classification},
author = {Kaile Du and Linyan Li and Fan Lyu and Fuyuan Hu and Zhenping Xia and Fenglei Xu},
journal= {arXiv preprint arXiv:2207.07840},
year = {2022}
}
Comments
arXiv admin note: substantial text overlap with arXiv:2203.05534