DSS:一种在类别增量学习中保留知识的多样化样本选择方法
DSS: A Diverse Sample Selection Method to Preserve Knowledge in Class-Incremental Learning
AI总结:
针对增量学习中样本选择多样性不足影响灾难性遗忘缓解效果的问题,提出DSS多样化样本选择方法,适用于两类任务边界的类别增量学习,性能优于SOTA且更易理解实现。
摘要:
基于排练的技术常被用于缓解增量学习(IL)中的灾难性遗忘(CF)问题。为此目的所选样本的质量十分重要,但大多数方法都无法确保所选样本具备恰当的多样性。我们提出了一种名为DSS(多样化样本选择)的新技术,可在不相交和模糊任务边界两种场景下的类别增量学习(CIL)设置中,从输入数据流中选择样本。我们的方法性能优于现有最优方法,且理解与实现难度都低得多。
英文摘要:
Rehearsal-based techniques are commonly used to mitigate catastrophic forgetting (CF) in Incremental learning (IL). The quality of the exemplars selected is important for this purpose and most methods do not ensure the appropriate diversity of the selected exemplars. We propose a new technique "DSS" -- Diverse Selection of Samples from the input data stream in the Class-incremental learning (CIL) setup under both disjoint and fuzzy task boundary scenarios. Our method outperforms state-of-the-art methods and is much simpler to understand and implement.
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。