ClaRe: Practical Class Incremental Learning By Remembering Previous Class Representations

by   Bahram Mohammadi, et al.

This paper presents a practical and simple yet efficient method to effectively deal with the catastrophic forgetting for Class Incremental Learning (CIL) tasks. CIL tends to learn new concepts perfectly, but not at the expense of performance and accuracy for old data. Learning new knowledge in the absence of data instances from previous classes or even imbalance samples of both old and new classes makes CIL an ongoing challenging problem. These issues can be tackled by storing exemplars belonging to the previous tasks or by utilizing the rehearsal strategy. Inspired by the rehearsal strategy with the approach of using generative models, we propose ClaRe, an efficient solution for CIL by remembering the representations of learned classes in each increment. Taking this approach leads to generating instances with the same distribution of the learned classes. Hence, our model is somehow retrained from the scratch using a new training set including both new and the generated samples. Subsequently, the imbalance data problem is also solved. ClaRe has a better generalization than prior methods thanks to producing diverse instances from the distribution of previously learned classes. We comprehensively evaluate ClaRe on the MNIST benchmark. Results show a very low degradation on accuracy against facing new knowledge over time. Furthermore, contrary to the most proposed solutions, the memory limitation is not problematic any longer which is considered as a consequential issue in this research area.



There are no comments yet.


page 1

page 2

page 3

page 4


Knowledge Distillation for Incremental Learning in Semantic Segmentation

Although deep learning architectures have shown remarkable results in sc...

Large Scale Incremental Learning

Modern machine learning suffers from catastrophic forgetting when learni...

Incremental Concept Learning via Online Generative Memory Recall

The ability to learn more and more concepts over time from incrementally...

Generative Feature Replay For Class-Incremental Learning

Humans are capable of learning new tasks without forgetting previous one...

IB-DRR: Incremental Learning with Information-Back Discrete Representation Replay

Incremental learning aims to enable machine learning models to continuou...

Drift-Aware Multi-Memory Model for Imbalanced Data Streams

Online class imbalance learning deals with data streams that are affecte...

Learning to Segment the Tail

Real-world visual recognition requires handling the extreme sample imbal...
This week in AI

Get the week's most popular data science and artificial intelligence research sent straight to your inbox every Saturday.