Class Incremental Learning from First Principles: A Review

Published: 10 Feb 2025, Last Modified: 10 Feb 2025Accepted by TMLREveryoneRevisionsBibTeXCC BY 4.0
Abstract: Continual learning systems attempt to efficiently learn over time without forgetting previously acquired knowledge. In recent years, there has been an explosion of work on continual learning, mainly focused on the class-incremental learning (CIL) setting. In this review, we take a step back and reconsider the CIL problem. We reexamine the problem definition and describe its unique challenges, contextualize existing solutions by analyzing non-continual approaches, and investigate the implications of various problem configurations. Our goal is to provide an alternative perspective to existing work on CIL and direct attention toward unexplored aspects of the problem.
Certifications: Survey Certification
Submission Length: Long submission (more than 12 pages of main content)
Changes Since Last Submission: For the camera-ready version, we have removed the green text highlighting recent changes, fixed the reference formatting, and made small updates to correct typos and improve explanations. As this is a survey without new empirical results, there is no code to submit.
Assigned Action Editor: ~Erin_Grant1
Submission Number: 3355
Loading