TY - CONF
T1 - WANDERING WITHIN A WORLD
T2 - 9th International Conference on Learning Representations, ICLR 2021
AU - Ren, Mengye
AU - Iuzzolino, Michael L.
AU - Mozer, Michael C.
AU - Zemel, Richard S.
N1 - Funding Information:
Acknowledgments: We thank Fei Sha, James Lucas, Eleni Triantafillou and Tyler Scott for helpful feedback on an earlier draft of the manuscript. Resources used in preparing this research were provided, in part, by the Province of Ontario, the Government of Canada through CIFAR, and companies sponsoring the Vector Institute (www.vectorinstitute.ai/#partners). This project is supported by NSERC and the Intelligence Advanced Research Projects Activity (IARPA) via Department of Interior/Interior Business Center (DoI/IBC) contract number D16PC00003. The U.S. Government is authorized to reproduce and distribute reprints for Governmental purposes notwithstanding any copyright annotation thereon. Disclaimer: The views and conclusions contained herein are those of the authors and should not be interpreted as necessarily representing the official policies or endorsements, either expressed or implied, of IARPA, DoI/IBC, or the U.S. Government.
Publisher Copyright:
© 2021 ICLR 2021 - 9th International Conference on Learning Representations. All rights reserved.
PY - 2021
Y1 - 2021
N2 - We aim to bridge the gap between typical human and machine-learning environments by extending the standard framework of few-shot learning to an online, continual setting. In this setting, episodes do not have separate training and testing phases, and instead models are evaluated online while learning novel classes. As in the real world, where the presence of spatiotemporal context helps us retrieve learned skills in the past, our online few-shot learning setting also features an underlying context that changes throughout time. Object classes are correlated within a context and inferring the correct context can lead to better performance. Building upon this setting, we propose a new few-shot learning dataset based on large scale indoor imagery that mimics the visual experience of an agent wandering within a world. Furthermore, we convert popular few-shot learning approaches into online versions and we also propose a new contextual prototypical memory model that can make use of spatiotemporal contextual information from the recent past.
AB - We aim to bridge the gap between typical human and machine-learning environments by extending the standard framework of few-shot learning to an online, continual setting. In this setting, episodes do not have separate training and testing phases, and instead models are evaluated online while learning novel classes. As in the real world, where the presence of spatiotemporal context helps us retrieve learned skills in the past, our online few-shot learning setting also features an underlying context that changes throughout time. Object classes are correlated within a context and inferring the correct context can lead to better performance. Building upon this setting, we propose a new few-shot learning dataset based on large scale indoor imagery that mimics the visual experience of an agent wandering within a world. Furthermore, we convert popular few-shot learning approaches into online versions and we also propose a new contextual prototypical memory model that can make use of spatiotemporal contextual information from the recent past.
UR - http://www.scopus.com/inward/record.url?scp=85132993625&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85132993625&partnerID=8YFLogxK
M3 - Paper
AN - SCOPUS:85132993625
Y2 - 3 May 2021 through 7 May 2021
ER -