Learning to Learn How to Learn: Self-Adaptive Visual Navigation Using Meta-Learning

Mitchell Wortsman, Kiana Ehsani, Mohammad Rastegari, Ali Farhadi, Roozbeh Mottaghi; The IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2019, pp. 6750-6759

Abstract


Learning is an inherently continuous phenomenon. When humans learn a new task there is no explicit distinction between training and inference. As we learn a task, we keep learning about it while performing the task. What we learn and how we learn it varies during different stages of learning. Learning how to learn and adapt is a key property that enables us to generalize effortlessly to new settings. This is in contrast with conventional settings in machine learning where a trained model is frozen during inference. In this paper we study the problem of learning to learn at both training and test time in the context of visual navigation. A fundamental challenge in navigation is generalization to unseen scenes. In this paper we propose a self-adaptive visual navigation method (SAVN) which learns to adapt to new environments without any explicit supervision. Our solution is a meta-reinforcement learning approach where an agent learns a self-supervised interaction loss that encourages effective navigation. Our experiments, performed in the AI2-THOR framework, show major improvements in both success rate and SPL for visual navigation in novel scenes. Our code and data are available at: https://github.com/allenai/savn.

Related Material


[pdf] [supp]
[bibtex]
@InProceedings{Wortsman_2019_CVPR,
author = {Wortsman, Mitchell and Ehsani, Kiana and Rastegari, Mohammad and Farhadi, Ali and Mottaghi, Roozbeh},
title = {Learning to Learn How to Learn: Self-Adaptive Visual Navigation Using Meta-Learning},
booktitle = {The IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},
month = {June},
year = {2019}
}