DER: Dynamically Expandable Representation for Class Incremental Learning

TL;DR

This paper introduces a novel two-stage approach with dynamically expandable representations for class incremental learning, improving stability and plasticity in vision models with limited memory.

Contribution

It proposes a dynamic expansion method with a channel-level pruning strategy and auxiliary loss to better integrate new concepts while retaining previous knowledge.

Findings

Outperforms existing methods on three benchmarks

Achieves better stability-plasticity trade-off

Effectively models complex novel concepts

Abstract

We address the problem of class incremental learning, which is a core step towards achieving adaptive vision intelligence. In particular, we consider the task setting of incremental learning with limited memory and aim to achieve better stability-plasticity trade-off. To this end, we propose a novel two-stage learning approach that utilizes a dynamically expandable representation for more effective incremental concept modeling. Specifically, at each incremental step, we freeze the previously learned representation and augment it with additional feature dimensions from a new learnable feature extractor. This enables us to integrate new visual concepts with retaining learned knowledge. We dynamically expand the representation according to the complexity of novel concepts by introducing a channel-level mask-based pruning strategy. Moreover, we introduce an auxiliary loss to encourage the model to learn diverse and discriminate features for novel concepts. We conduct extensive experiments on the three class incremental learning benchmarks and our method consistently outperforms other methods with a large margin.