A Model or 603 Exemplars: Towards Memory-Efficient Class-Incremental Learning

TL;DR

This paper investigates the effectiveness of saving models versus exemplars in class-incremental learning, emphasizing the importance of fair memory budget comparisons and proposing a memory-efficient model extension called MEMO.

Contribution

It introduces a holistic evaluation framework for CIL methods considering memory size and accuracy, and proposes MEMO, a simple baseline that enhances memory efficiency by leveraging shared representations.

Findings

Saving models does not always improve performance when memory budgets are aligned.

Memory buffer construction impacts CIL performance significantly.

MEMO achieves competitive results with modest memory overhead.

Abstract

Real-world applications require the classification model to adapt to new classes without forgetting old ones. Correspondingly, Class-Incremental Learning (CIL) aims to train a model with limited memory size to meet this requirement. Typical CIL methods tend to save representative exemplars from former classes to resist forgetting, while recent works find that storing models from history can substantially boost the performance. However, the stored models are not counted into the memory budget, which implicitly results in unfair comparisons. We find that when counting the model size into the total budget and comparing methods with aligned memory size, saving models do not consistently work, especially for the case with limited memory budgets. As a result, we need to holistically evaluate different CIL methods at different memory scales and simultaneously consider accuracy and memory size for measurement. On the other hand, we dive deeply into the construction of the memory buffer for memory efficiency. By analyzing the effect of different layers in the network, we find that shallow and deep layers have different characteristics in CIL. Motivated by this, we propose a simple yet effective baseline, denoted as MEMO for Memory-efficient Expandable MOdel. MEMO extends specialized layers based on the shared generalized representations, efficiently extracting diverse representations with modest cost and maintaining representative exemplars. Extensive experiments on benchmark datasets validate MEMO's competitive performance. Code is available at: https://github.com/wangkiw/ICLR23-MEMO