Class-Incremental Mixture of Gaussians for Deep Continual Learning

TL;DR

This paper introduces a novel class-incremental continual learning method that integrates a mixture of Gaussians model with deep feature extractors, enabling effective learning without memory and outperforming existing approaches.

Contribution

It presents an end-to-end gradient-based approach to incorporate mixture of Gaussians into continual learning, handling class-incremental scenarios without relying on memory buffers.

Findings

Effective in memory-free scenarios

Competitive with state-of-the-art methods

Successful joint optimization of features and class representations

Abstract

Continual learning models for stationary data focus on learning and retaining concepts coming to them in a sequential manner. In the most generic class-incremental environment, we have to be ready to deal with classes coming one by one, without any higher-level grouping. This requirement invalidates many previously proposed methods and forces researchers to look for more flexible alternative approaches. In this work, we follow the idea of centroid-driven methods and propose end-to-end incorporation of the mixture of Gaussians model into the continual learning framework. By employing the gradient-based approach and designing losses capable of learning discriminative features while avoiding degenerate solutions, we successfully combine the mixture model with a deep feature extractor allowing for joint optimization and adjustments in the latent space. Additionally, we show that our model can effectively learn in memory-free scenarios with fixed extractors. In the conducted experiments, we empirically demonstrate the effectiveness of the proposed solutions and exhibit the competitiveness of our model when compared with state-of-the-art continual learning baselines evaluated in the context of image classification problems.