Knowledge Restore and Transfer for Multi-label Class-Incremental Learning
This work addresses the problem of catastrophic forgetting in multi-label class-incremental learning, which is more practical but rarely studied compared to single-label tasks, representing an incremental advancement.
The paper tackles multi-label class-incremental learning (MLCIL), addressing catastrophic forgetting due to label absence and information dilution, by proposing a knowledge restore and transfer framework with dynamic pseudo-label and incremental cross-attention modules, achieving improved recognition performance on MS-COCO and PASCAL VOC datasets.
Current class-incremental learning research mainly focuses on single-label classification tasks while multi-label class-incremental learning (MLCIL) with more practical application scenarios is rarely studied. Although there have been many anti-forgetting methods to solve the problem of catastrophic forgetting in class-incremental learning, these methods have difficulty in solving the MLCIL problem due to label absence and information dilution. In this paper, we propose a knowledge restore and transfer (KRT) framework for MLCIL, which includes a dynamic pseudo-label (DPL) module to restore the old class knowledge and an incremental cross-attention(ICA) module to save session-specific knowledge and transfer old class knowledge to the new model sufficiently. Besides, we propose a token loss to jointly optimize the incremental cross-attention module. Experimental results on MS-COCO and PASCAL VOC datasets demonstrate the effectiveness of our method for improving recognition performance and mitigating forgetting on multi-label class-incremental learning tasks.