Tackling Online One-Class Incremental Learning by Removing Negative Contrasts

03/24/2022
by   Nader Asadi, et al.
0

Recent work studies the supervised online continual learning setting where a learner receives a stream of data whose class distribution changes over time. Distinct from other continual learning settings the learner is presented new samples only once and must distinguish between all seen classes. A number of successful methods in this setting focus on storing and replaying a subset of samples alongside incoming data in a computationally efficient manner. One recent proposal ER-AML achieved strong performance in this setting by applying an asymmetric loss based on contrastive learning to the incoming data and replayed data. However, a key ingredient of the proposed method is avoiding contrasts between incoming data and stored data, which makes it impractical for the setting where only one new class is introduced in each phase of the stream. In this work we adapt a recently proposed approach (BYOL) from self-supervised learning to the supervised learning setting, unlocking the constraint on contrasts. We then show that supplementing this with additional regularization on class prototypes yields a new method that achieves strong performance in the one-class incremental learning setting and is competitive with the top performing methods in the multi-class incremental setting.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
10/17/2021

Online Continual Learning Via Candidates Voting

Continual learning in online scenario aims to learn a sequence of new ta...
research
01/25/2021

Online Continual Learning in Image Classification: An Empirical Survey

Online continual learning for image classification studies the problem o...
research
08/20/2023

A Comprehensive Empirical Evaluation on Online Continual Learning

Online continual learning aims to get closer to a live learning experien...
research
03/19/2023

SIESTA: Efficient Online Continual Learning with Sleep

In supervised continual learning, a deep neural network (DNN) is updated...
research
02/11/2022

Exemplar-free Online Continual Learning

Targeted for real world scenarios, online continual learning aims to lea...
research
02/01/2023

Towards Label-Efficient Incremental Learning: A Survey

The current dominant paradigm when building a machine learning model is ...
research
10/20/2021

Class Incremental Online Streaming Learning

A wide variety of methods have been developed to enable lifelong learnin...

Please sign up or login with your details

Forgot password? Click here to reset