DeepAI AI Chat
Log In Sign Up

iCaRL: Incremental Classifier and Representation Learning

by   Sylvestre-Alvise Rebuffi, et al.

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.


page 8

page 12

page 13

page 14

page 15


HCIL: Hierarchical Class Incremental Learning for Longline Fishing Visual Monitoring

The goal of electronic monitoring of longline fishing is to visually mon...

Few-Shot Class-Incremental Learning

The ability to incrementally learn new classes is crucial to the develop...

Batchwise Probabilistic Incremental Data Cleaning

Lack of data and data quality issues are among the main bottlenecks that...

Learning without Memorizing

Incremental learning (IL) is an important task aimed to increase the cap...

Class-incremental Learning with Pre-allocated Fixed Classifiers

In class-incremental learning, a learning agent faces a stream of data w...

Energy-based Latent Aligner for Incremental Learning

Deep learning models tend to forget their earlier knowledge while increm...

CatNet: Class Incremental 3D ConvNets for Lifelong Egocentric Gesture Recognition

Egocentric gestures are the most natural form of communication for human...

Code Repositories