iCaRL: Incremental Classifier and Representation Learning
Abstract
A major open problem on the road to artificial intelligence is the development of incrementally learning systems that learn about more and more concepts over time from a stream of data. In this work, we introduce a new training strategy, iCaRL, that allows learning in such a class-incremental way: only the training data for a small number of classes has to be present at the same time and new classes can be added progressively. iCaRL learns strong classifiers and a data representation simultaneously. This distinguishes it from earlier works that were fundamentally limited to fixed data representations and therefore incompatible with deep learning architectures. We show by experiments on CIFAR-100 and ImageNet ILSVRC 2012 data that iCaRL can learn many classes incrementally over a long period of time where other strategies quickly fail.
Cite
@article{arxiv.1611.07725,
title = {iCaRL: Incremental Classifier and Representation Learning},
author = {Sylvestre-Alvise Rebuffi and Alexander Kolesnikov and Georg Sperl and Christoph H. Lampert},
journal= {arXiv preprint arXiv:1611.07725},
year = {2017}
}
Comments
Accepted paper at CVPR 2017