ACAE-REMIND for Online Continual Learning with Compressed Feature Replay

05/18/2021
by   Kai Wang, et al.
0

Online continual learning aims to learn from a non-IID stream of data from a number of different tasks, where the learner is only allowed to consider data once. Methods are typically allowed to use a limited buffer to store some of the images in the stream. Recently, it was found that feature replay, where an intermediate layer representation of the image is stored (or generated) leads to superior results than image replay, while requiring less memory. Quantized exemplars can further reduce the memory usage. However, a drawback of these methods is that they use a fixed (or very intransigent) backbone network. This significantly limits the learning of representations that can discriminate between all tasks. To address this problem, we propose an auxiliary classifier auto-encoder (ACAE) module for feature replay at intermediate layers with high compression rates. The reduced memory footprint per image allows us to save more exemplars for replay. In our experiments, we conduct task-agnostic evaluation under online continual learning setting and get state-of-the-art performance on ImageNet-Subset, CIFAR100 and CIFAR10 dataset.

READ FULL TEXT
POST COMMENT

Comments

There are no comments yet.

Authors

page 1

page 2

page 3

page 4

08/11/2019

Online Continual Learning with Maximally Interfered Retrieval

Continual learning, the setting where a learning agent is faced with a n...
10/06/2020

The Effectiveness of Memory Replay in Large Scale Continual Learning

We study continual learning in the large scale setting where tasks in th...
11/19/2019

Online Learned Continual Compression with Stacked Quantization Module

We introduce and study the problem of Online Continual Compression, wher...
07/16/2020

Multilayer Neuromodulated Architectures for Memory-Constrained Online Continual Learning

We focus on the problem of how to achieve online continual learning unde...
11/03/2021

One Pass ImageNet

We present the One Pass ImageNet (OPIN) problem, which aims to study the...
10/20/2021

A TinyML Platform for On-Device Continual Learning with Quantized Latent Replays

In the last few years, research and development on Deep Learning models ...
07/22/2020

Memory-Latency-Accuracy Trade-offs for Continual Learning on a RISC-V Extreme-Edge Node

AI-powered edge devices currently lack the ability to adapt their embedd...
This week in AI

Get the week's most popular data science and artificial intelligence research sent straight to your inbox every Saturday.