DSS: A Diverse Sample Selection Method to Preserve Knowledge in Class-Incremental Learning
CoRR(2023)
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.
更多查看译文
关键词
Incremental Learning,Continual Learning,Machine Learning,Class-Incremental Learning,Catastrophic Forgetting
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络
Chat Paper
正在生成论文摘要