Exemplar-free Online Continual Learning

02/11/2022
by   Jiangpeng He, et al.
0

Targeted for real world scenarios, online continual learning aims to learn new tasks from sequentially available data under the condition that each data is observed only once by the learner. Though recent works have made remarkable achievements by storing part of learned task data as exemplars for knowledge replay, the performance is greatly relied on the size of stored exemplars while the storage consumption is a significant constraint in continual learning. In addition, storing exemplars may not always be feasible for certain applications due to privacy concerns. In this work, we propose a novel exemplar-free method by leveraging nearest-class-mean (NCM) classifier where the class mean is estimated during training phase on all data seen so far through online mean update criteria. We focus on image classification task and conduct extensive experiments on benchmark datasets including CIFAR-100 and Food-1k. The results demonstrate that our method without using any exemplar outperforms state-of-the-art exemplar-based approaches with large margins under standard protocol (20 exemplars per class) and is able to achieve competitive performance even with larger exemplar size (100 exemplars per class).

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
08/15/2021

Online Continual Learning For Visual Food Classification

Food image classification is challenging for real-world applications sin...
research
04/12/2022

Out-Of-Distribution Detection In Unsupervised Continual Learning

Unsupervised continual learning aims to learn new tasks incrementally wi...
research
03/30/2023

Mole Recruitment: Poisoning of Image Classifiers via Selective Batch Sampling

In this work, we present a data poisoning attack that confounds machine ...
research
04/14/2021

Continual Learning From Unlabeled Data Via Deep Clustering

Continual learning, a promising future learning strategy, aims to learn ...
research
03/24/2022

Tackling Online One-Class Incremental Learning by Removing Negative Contrasts

Recent work studies the supervised online continual learning setting whe...
research
05/06/2022

Continual Object Detection via Prototypical Task Correlation Guided Gating Mechanism

Continual learning is a challenging real-world problem for constructing ...

Please sign up or login with your details

Forgot password? Click here to reset