iCaRL: Incremental Classifier and Representation Learning

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: o...

Full description

Saved in:
Bibliographic Details
Published in:2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) pp. 5533 - 5542
Main Authors: Rebuffi, Sylvestre-Alvise, Kolesnikov, Alexander, Sperl, Georg, Lampert, Christoph H.
Format: Conference Proceeding
Language:English
Published: IEEE 01.07.2017
Subjects:
Classification algorithms
Computer vision
Feature extraction
Memory management
Prototypes
Training
Training data
ISSN:1063-6919, 1063-6919
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary: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.
ISSN:1063-6919
1063-6919
DOI:10.1109/CVPR.2017.587