Pith

open record

sign in

arxiv: 2108.09020 · v2 · pith:NQNAJPFF · submitted 2021-08-20 · cs.LG · cs.CV

Online Continual Learning with Natural Distribution Shifts: An Empirical Study with Visual Data

Reviewed by Pith T0 review T1 audit T2 compute T3 formal T4 kernel pith:NQNAJPFFrecord.jsonopen to challenge →

classification cs.LG cs.CV
keywords learningcontinualonlinedataaddedtimedistributiongradient-based
0
0 comments X
read the original abstract

Continual learning is the problem of learning and retaining knowledge through time over multiple tasks and environments. Research has primarily focused on the incremental classification setting, where new tasks/classes are added at discrete time intervals. Such an "offline" setting does not evaluate the ability of agents to learn effectively and efficiently, since an agent can perform multiple learning epochs without any time limitation when a task is added. We argue that "online" continual learning, where data is a single continuous stream without task boundaries, enables evaluating both information retention and online learning efficacy. In online continual learning, each incoming small batch of data is first used for testing and then added to the training set, making the problem truly online. Trained models are later evaluated on historical data to assess information retention. We introduce a new benchmark for online continual visual learning that exhibits large scale and natural distribution shifts. Through a large-scale analysis, we identify critical and previously unobserved phenomena of gradient-based optimization in continual learning, and propose effective strategies for improving gradient-based online continual learning with real data. The source code and dataset are available in: https://github.com/IntelLabs/continuallearning.

This paper has not been read by Pith yet.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.