在类增量学习中使领域偏移成为灾难性遗忘的缓解因素
Make Domain Shift a Catastrophic Forgetting Alleviator in Class-Incremental Learning
AI总结：
本文发现领域偏移能降低类增量学习中的遗忘率，据此提出基于轻量级原型池和对比学习的DisCo方法，通过分离任务间特征分布、减少参数干扰，显著提升多种现有CIL方法的性能。
摘要：
在类增量学习（CIL）领域，缓解灾难性遗忘问题是一个关键挑战。本文发现了一个反直觉的现象：通过将领域偏移引入CIL任务，遗忘率显著降低。我们的综合研究表明，引入领域偏移会使不同任务之间的特征分布更加清晰分离，并有助于减少学习过程中的参数干扰。受这一观察启发，我们提出了一种简单而有效的方法，名为DisCo，用于处理CIL任务。DisCo引入了一个轻量级原型池，利用对比学习促使当前任务相对于先前任务具有更鲜明的特征分布，从而有效缓解任务间的干扰。DisCo可以轻松集成到现有的最先进类增量学习方法中。实验结果表明，将我们的方法融入多种CIL方法能够取得显著的性能提升，验证了我们的方法通过分离特征表示和减少干扰来增强类增量学习的优势。这些发现表明，DisCo可以作为未来类增量学习研究中一种稳健的范式。
英文摘要：
In the realm of class-incremental learning (CIL), alleviating the catastrophic forgetting problem is a pivotal challenge. This paper discovers a counter-intuitive observation: by incorporating domain shift into CIL tasks, the forgetting rate is significantly reduced. Our comprehensive studies demonstrate that incorporating domain shift leads to a clearer separation in the feature distribution across tasks and helps reduce parameter interference during the learning process. Inspired by this observation, we propose a simple yet effective method named DisCo to deal with CIL tasks. DisCo introduces a lightweight prototype pool that utilizes contrastive learning to promote distinct feature distributions for the current task relative to previous ones, effectively mitigating interference across tasks. DisCo can be easily integrated into existing state-of-the-art class-incremental learning methods. Experimental results show that incorporating our method into various CIL methods achieves substantial performance improvements, validating the benefits of our approach in enhancing class-incremental learning by separating feature representation and reducing interference. These findings illustrate that DisCo can serve as a robust fashion for future research in class-incremental learning.
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。
