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.

翻译：当前类增量学习研究主要聚焦于单标签分类任务，而具有更广泛应用场景的多标签类增量学习（MLCIL）问题鲜有研究。尽管已有诸多抗遗忘方法用于解决类增量学习中的灾难性遗忘问题，但由于标签缺失与信息稀释，这些方法难以有效应对MLCIL挑战。本文提出一种面向MLCIL的知识恢复与迁移（KRT）框架，包含动态伪标签（DPL）模块用于恢复旧类知识，以及增量交叉注意力（ICA）模块用于保存会话特定知识并将旧类知识充分迁移至新模型。此外，我们提出一种令牌损失函数以联合优化增量交叉注意力模块。在MS-COCO和PASCAL VOC数据集上的实验结果表明，本方法能有效提升多标签类增量学习任务的识别性能并缓解遗忘问题。