Rainbow Memory: Continual Learning with a Memory of Diverse Samples

Continual learning is a realistic learning scenario for AI models. Prevalent scenario of continual learning, however, assumes disjoint sets of classes as tasks and is less realistic rather artificial. Instead, we focus on 'blurry' task boundary; where tasks shares classes and is more reali...

Full description

Saved in:
Bibliographic Details
Published in:Proceedings (IEEE Computer Society Conference on Computer Vision and Pattern Recognition. Online) pp. 8214 - 8223
Main Authors: Bang, Jihwan, Kim, Heesu, Yoo, YoungJoon, Ha, Jung-Woo, Choi, Jonghyun
Format: Conference Proceeding
Language:English
Published: IEEE 01.06.2021
Subjects:
Codes
Computer vision
Learning (artificial intelligence)
Memory management
Sampling methods
Training
Uncertainty
ISSN:1063-6919
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Continual learning is a realistic learning scenario for AI models. Prevalent scenario of continual learning, however, assumes disjoint sets of classes as tasks and is less realistic rather artificial. Instead, we focus on 'blurry' task boundary; where tasks shares classes and is more realistic and practical. To address such task, we argue the importance of diversity of samples in an episodic memory. To enhance the sample diversity in the memory, we propose a novel memory management strategy based on per-sample classification uncertainty and data augmentation, named Rainbow Memory (RM). With extensive empirical validations on MNIST, CIFAR10, CIFAR100, and ImageNet datasets, we show that the proposed method significantly improves the accuracy in blurry continual learning setups, outperforming state of the arts by large margins despite its simplicity. Code and data splits will be available in https://github.com/clovaai/rainbow-memory.
ISSN:1063-6919
DOI:10.1109/CVPR46437.2021.00812