Continual Representation Learning for Images with Variational Continual Auto-Encoder

Ik Jeon, Soo Shin

2019

Abstract

We propose a novel architecture for the continual representation learning for images, called variational continual auto-encoder (VCAE). Our approach builds a time-variant parametric model that generates images close to the observation by using optimized approximate inference over time. When the dataset is sequentially observed, the model efficiently learns underlying representations without forgetting previously acquired knowledge. Through experiments, we evaluate the development of test log-likelihood over time, which shows resistance to the catastrophic forgetting. The results show that VCAE has stronger immunity against catastrophic forgetting in comparison to the benchmark while VCAE requires much less time for training.

Paper Citation

in Harvard Style

Jeon I. and Shin S. (2019). Continual Representation Learning for Images with Variational Continual Auto-Encoder.In Proceedings of the 11th International Conference on Agents and Artificial Intelligence - Volume 2: ICAART, ISBN 978-989-758-350-6, pages 367-373. DOI: 10.5220/0007687103670373

in Bibtex Style

@conference{icaart19,
author={Ik Jeon and Soo Shin},
title={Continual Representation Learning for Images with Variational Continual Auto-Encoder},
booktitle={Proceedings of the 11th International Conference on Agents and Artificial Intelligence - Volume 2: ICAART,},
year={2019},
pages={367-373},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0007687103670373},
isbn={978-989-758-350-6},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 11th International Conference on Agents and Artificial Intelligence - Volume 2: ICAART,
TI - Continual Representation Learning for Images with Variational Continual Auto-Encoder
SN - 978-989-758-350-6
AU - Jeon I.
AU - Shin S.
PY - 2019
SP - 367
EP - 373
DO - 10.5220/0007687103670373