通过动态调整提示词，缓解多标签增量学习中的遗忘问题。
Dynamic Prompt Adjustment for Multi-Label Class-Incremental Learning
- 引入改进的数据回放与提示损失机制，增强模型对多标签任务的适应性。
- 在多个基准数据集上显著提升多标签增量学习性能，有效减少知识遗忘。
- 适合关注多标签学习、提示工程与持续学习的研究者参考。
单标签增量学习（SLCIL）已取得显著进展，但更贴近实际的多标签增量学习（MLCIL）仍研究不足。尽管视觉语言模型如CLIP在分类任务中表现优异，直接用于MLCIL会导致灾难性遗忘。为此，本文结合改进的数据回放机制与提示损失，抑制知识遗忘。具体而言，模型增强提示信息以更好适应多标签分类，并采用基于置信度的回放策略选择代表性样本。提示损失显著降低模型对旧知识的遗忘。实验表明，该方法在多个基准数据集上显著提升了MLCIL性能，验证了其有效性。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。