Distribution-Level Memory Recall for Continual Learning: Preserving Knowledge and Avoiding Confusion

TL;DR

This paper introduces the Distribution-Level Memory Recall (DMR) method for continual learning, which models old knowledge distributions with Gaussian mixtures to generate more accurate pseudo features, reducing confusion and improving knowledge retention.

Contribution

The paper proposes a novel distribution-level pseudo feature generation approach using Gaussian mixtures, and introduces methods to handle multimodal imbalance and quantify confusion in continual learning.

Findings

DMR outperforms prototype-based methods in preserving old knowledge.

IGIM effectively mitigates multimodal imbalance and confusion.

IMFE enhances pseudo features, reducing classification errors.

Abstract

Continual Learning (CL) aims to enable Deep Neural Networks (DNNs) to learn new data without forgetting previously learned knowledge. The key to achieving this goal is to avoid confusion at the feature level, i.e., avoiding confusion within old tasks and between new and old tasks. Previous prototype-based CL methods generate pseudo features for old knowledge replay by adding Gaussian noise to the centroids of old classes. However, the distribution in the feature space exhibits anisotropy during the incremental process, which prevents the pseudo features from faithfully reproducing the distribution of old knowledge in the feature space, leading to confusion in classification boundaries within old tasks. To address this issue, we propose the Distribution-Level Memory Recall (DMR) method, which uses a Gaussian mixture model to precisely fit the feature distribution of old knowledge at the distribution level and generate pseudo features in the next stage. Furthermore, resistance to confusion at the distribution level is also crucial for multimodal learning, as the problem of multimodal imbalance results in significant differences in feature responses between different modalities, exacerbating confusion within old tasks in prototype-based CL methods. Therefore, we mitigate the multi-modal imbalance problem by using the Inter-modal Guidance and Intra-modal Mining (IGIM) method to guide weaker modalities with prior information from dominant modalities and further explore useful information within modalities. For the second key, We propose the Confusion Index to quantitatively describe a model's ability to distinguish between new and old tasks, and we use the Incremental Mixup Feature Enhancement (IMFE) method to enhance pseudo features with new sample features, alleviating classification confusion between new and old knowledge.