Class Incremental Online Streaming Learning

TL;DR

This paper introduces CIOSL, a novel method for class-incremental online streaming learning that effectively handles single-pass data streams with class correlations, using dual regularization and experience replay to improve performance.

Contribution

The paper proposes CIOSL, a new approach combining implicit and explicit regularization with an efficient replay strategy for online streaming class-incremental learning.

Findings

CIOSL outperforms existing methods on challenging datasets.

Dual regularization improves model stability and accuracy.

Efficient replay strategy enhances learning in single-pass data streams.

Abstract

A wide variety of methods have been developed to enable lifelong learning in conventional deep neural networks. However, to succeed, these methods require a `batch' of samples to be available and visited multiple times during training. While this works well in a static setting, these methods continue to suffer in a more realistic situation where data arrives in \emph{online streaming manner}. We empirically demonstrate that the performance of current approaches degrades if the input is obtained as a stream of data with the following restrictions: $(i)$ each instance comes one at a time and can be seen only once, and $(ii)$ the input data violates the i.i.d assumption, i.e., there can be a class-based correlation. We propose a novel approach (CIOSL) for the class-incremental learning in an \emph{online streaming setting} to address these challenges. The proposed approach leverages implicit and explicit dual weight regularization and experience replay. The implicit regularization is leveraged via the knowledge distillation, while the explicit regularization incorporates a novel approach for parameter regularization by learning the joint distribution of the buffer replay and the current sample. Also, we propose an efficient online memory replay and replacement buffer strategy that significantly boosts the model's performance. Extensive experiments and ablation on challenging datasets show the efficacy of the proposed method.