iCaRL: Incremental Classifier and Representation Learning

Sylvestre-Alvise Rebuffi, Alexander Kolesnikov, Georg Sperl, Christoph H. Lampert

CVPR 2017

doi:10.1109/CVPR.2017.587 /cvpr/2017/rebuffi2017cvpr-icarl/

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.

PDF CVPR Semantic Scholar

Cite

Text

Rebuffi et al. "iCaRL: Incremental Classifier and Representation Learning." Conference on Computer Vision and Pattern Recognition, 2017. doi:10.1109/CVPR.2017.587

Markdown

[Rebuffi et al. "iCaRL: Incremental Classifier and Representation Learning." Conference on Computer Vision and Pattern Recognition, 2017.](https://mlanthology.org/cvpr/2017/rebuffi2017cvpr-icarl/) doi:10.1109/CVPR.2017.587

BibTeX

@inproceedings{rebuffi2017cvpr-icarl,
  title     = {{iCaRL: Incremental Classifier and Representation Learning}},
  author    = {Rebuffi, Sylvestre-Alvise and Kolesnikov, Alexander and Sperl, Georg and Lampert, Christoph H.},
  booktitle = {Conference on Computer Vision and Pattern Recognition},
  year      = {2017},
  doi       = {10.1109/CVPR.2017.587},
  url       = {https://mlanthology.org/cvpr/2017/rebuffi2017cvpr-icarl/}
}