Adversarial Continual Learning
Sayna Ebrahimi, Franziska Meier, Roberto Calandra, Trevor Darrell, Marcus Rohrbach
Abstract
Continual learning aims to learn new tasks without forgetting previously learned ones. We hypothesize that representations learned to solve each task in a sequence have a shared structure while containing some task-specific properties. We show that shared features are significantly less prone to forgetting and propose a novel hybrid continual learning framework that learns a disjoint representation for task-invariant and task-specific features required to solve a sequence of tasks. Our model combines architecture growth to prevent forgetting of task-specific skills and an experience replay approach to preserve shared skills. We demonstrate our hybrid approach is effective in avoiding forgetting and show it is superior to both architecture-based and memory-based approaches on class incrementally learning of a single dataset as well as a sequence of multiple datasets in image classification. Our code is available at https://github.com/facebookresearch/Adversarial-Continual-Learning
BibTeX
@inproceedings{eccv2020_adversarialconti,
title = {Adversarial Continual Learning},
author = {Sayna Ebrahimi and Franziska Meier and Roberto Calandra and Trevor Darrell and Marcus Rohrbach},
booktitle = {ECCV 2020},
year = {2020}
}