Continual Learning in the Presence of Repetition

TL;DR

This paper discusses the importance of repetition in data streams for continual learning, highlighting challenge solutions that leverage repeated information to improve model adaptation in evolving environments.

Contribution

It introduces the CLVision challenge focusing on repetition in class-incremental learning and presents ensemble-based solutions that utilize repeated data for continual adaptation.

Findings

Ensemble solutions effectively exploit data repetition.

Repetition in data streams enhances continual learning performance.

Challenge results demonstrate the potential of repetition-aware strategies.

Abstract

Continual learning (CL) provides a framework for training models in ever-evolving environments. Although re-occurrence of previously seen objects or tasks is common in real-world problems, the concept of repetition in the data stream is not often considered in standard benchmarks for CL. Unlike with the rehearsal mechanism in buffer-based strategies, where sample repetition is controlled by the strategy, repetition in the data stream naturally stems from the environment. This report provides a summary of the CLVision challenge at CVPR 2023, which focused on the topic of repetition in class-incremental learning. The report initially outlines the challenge objective and then describes three solutions proposed by finalist teams that aim to effectively exploit the repetition in the stream to learn continually. The experimental results from the challenge highlight the effectiveness of ensemble-based solutions that employ multiple versions of similar modules, each trained on different but overlapping subsets of classes. This report underscores the transformative potential of taking a different perspective in CL by employing repetition in the data stream to foster innovative strategy design.