面向多标签类增量学习的动态提示调整
Dynamic Prompt Adjustment for Multi-Label Class-Incremental Learning
AI总结：
本文针对多标签类增量学习中的灾难性遗忘问题，提出结合改进数据回放机制与提示损失的动态提示调整方法，在多个基准数据集上显著提升MLCIL性能。
摘要：
单标签增量学习（SLCIL）已取得显著进展，然而更实用且更具挑战性的多标签类增量学习（MLCIL）仍研究不足。近年来，CLIP等视觉语言模型在分类任务中取得了良好效果。然而，直接使用CLIP解决MLCIL问题会导致灾难性遗忘。为解决这一问题，我们整合了一种改进的数据回放机制和提示损失以抑制知识遗忘。具体而言，我们的模型增强了提示信息以更好地适应多标签分类任务，并采用基于置信度的回放策略选择代表性样本。此外，提示损失显著降低了模型对先前知识的遗忘。实验结果表明，我们的方法在多个基准数据集上大幅提升了MLCIL任务的性能，验证了其有效性。
英文摘要：
Significant advancements have been made in single label incremental learning (SLCIL),yet the more practical and challenging multi label class incremental learning (MLCIL) remains understudied. Recently,visual language models such as CLIP have achieved good results in classification tasks. However,directly using CLIP to solve MLCIL issue can lead to catastrophic forgetting. To tackle this issue, we integrate an improved data replay mechanism and prompt loss to curb knowledge forgetting. Specifically,our model enhances the prompt information to better adapt to multi-label classification tasks and employs confidence-based replay strategy to select representative samples. Moreover, the prompt loss significantly reduces the model's forgetting of previous knowledge. Experimental results demonstrate that our method has substantially improved the performance of MLCIL tasks across multiple benchmark datasets,validating its effectiveness.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
