English

Class-incremental Learning using a Sequence of Partial Implicitly Regularized Classifiers

Machine Learning 2021-06-01 v3

Abstract

In class-incremental learning, the objective is to learn a number of classes sequentially without having access to the whole training data. However, due to a problem known as catastrophic forgetting, neural networks suffer substantial performance drop in such settings. The problem is often approached by experience replay, a method which stores a limited number of samples to be replayed in future steps to reduce forgetting of the learned classes. When using a pretrained network as a feature extractor, we show that instead of training a single classifier incrementally, it is better to train a number of specialized classifiers which do not interfere with each other yet can cooperatively predict a single class. Our experiments on CIFAR100 dataset show that the proposed method improves the performance over SOTA by a large margin.

Keywords

Cite

@article{arxiv.2104.01577,
  title  = {Class-incremental Learning using a Sequence of Partial Implicitly Regularized Classifiers},
  author = {Sobirdzhon Bobiev and Adil Khan and Syed Muhammad Ahsan Raza Kazmi},
  journal= {arXiv preprint arXiv:2104.01577},
  year   = {2021}
}