.png){kind=icon}
返回
Multi-Label Continual Learning Using Augmented Graph Convolutional Network
.png){kind=icon}
OA
AI
DOI：10.1109/TMM.2023.3305871.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
Multi-Label Continual Learning (MLCL) is a framework designed for class-incremental multi-label image recognition. However, MLCL faces two critical challenges: the construction of label relationships on past-missing and future-missing partial labels of training data, and the problem of catastrophic forgetting, which leads to poor generalization. To address these challenges, this study proposes an enhanced version of the Augmented Graph Convolutional Network (AGCN++), capable of constructing cross-task label relationships and mitigating catastrophic forgetting. First, an Augmented Correlation Matrix (ACM) is constructed across all observed classes, incorporating intra-task relationships derived from hard label statistics. Additionally, inter-task relationships are established by leveraging both hard and soft labels obtained from the data, as well as a constructed expert network. Next, a novel partial label encoder (PLE) is introduced for MLCL, enabling the extraction of dynamic class representations for each partial label image as graph nodes. This PLE also facilitates the generation of soft labels, which contribute to the creation of a more persuasive ACM and effectively mitigate forgetting. Lastly, a relationship-preserving constrainter is proposed to address the issue of forgetting label dependencies across old tasks. In the AGCN++, the label relationships topology can be augmented automatically, thereby generating efficient class representations. The effectiveness of the proposed method is evaluated using two multi-label image benchmarks. The experimental results demonstrate that the proposed approach is highly effective in the context of MLCL image recognition. It can establish compelling correlations across tasks, even in scenarios where the old task labels are missing.
Keyword:
Task analysis
Correlation
Training
Image recognition
Convolutional neural networks
Dogs
Recurrent neural networks
Continual learning
multi-label recognition
partial label encoder
augmented correlation matrix
期刊
IF:
9.7
论文数:
4.6K
被引数:
2.4W
机构
引用论文
.png){kind=icon}
Clinicopathologic profile of 470 giant cell tumors of bone from a cancer hospital in western India
PREAI
分享收藏
查看更多内容