Online continual learning in image classification: An empirical survey
Neurocomputing(2022)
摘要
Online continual learning for image classification studies the problem of learning to classify images from an online stream of data and tasks, where tasks may include new classes (class incremental) or data nonstationarity (domain incremental). One of the key challenges of continual learning is to avoid catastrophic forgetting (CF), i.e., forgetting old tasks in the presence of more recent tasks. Over the past few years, a large range of methods and tricks have been introduced to address the continual learning problem, but many have not been fairly and systematically compared under a variety of realistic and practical settings.
更多查看译文
关键词
Incremental learning,Continual learning,Lifelong learning,Catastrophic forgetting,Online learning
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络