Adaptive Margin Global Classifier for Exemplar-Free Class-Incremental Learning

TL;DR

This paper introduces AMGC, a novel classifier for exemplar-free class-incremental learning that addresses bias and distribution issues, achieving superior classification performance through adaptive margin softmax loss.

Contribution

The paper proposes the Adaptive Margin Global Classifier (AMGC), combining a distribution-based global classifier with variance enlarging to improve EFCIL performance.

Findings

AMGC outperforms existing methods on EFCIL benchmarks.

The adaptive margin softmax loss enhances class separation.

Extensive experiments validate the effectiveness of AMGC.

Abstract

Exemplar-free class-incremental learning (EFCIL) presents a significant challenge as the old class samples are absent for new task learning. Due to the severe imbalance between old and new class samples, the learned classifiers can be easily biased toward the new ones. Moreover, continually updating the feature extractor under EFCIL can compromise the discriminative power of old class features, e.g., leading to less compact and more overlapping distributions across classes. Existing methods mainly focus on handling biased classifier learning. In this work, both cases are considered using the proposed method. Specifically, we first introduce a Distribution-Based Global Classifier (DBGC) to avoid bias factors in existing methods, such as data imbalance and sampling. More importantly, the compromised distributions of old classes are simulated via a simple operation, variance enlarging (VE). Incorporating VE based on DBGC results in a novel classification loss for EFCIL. This loss is proven equivalent to an Adaptive Margin Softmax Cross Entropy (AMarX). The proposed method is thus called Adaptive Margin Global Classifier (AMGC). AMGC is simple yet effective. Extensive experiments show that AMGC achieves superior image classification results on its own under a challenging EFCIL setting. Detailed analysis is also provided for further demonstration.