Planned intervention: On Wednesday June 26th 05:30 UTC Zenodo will be unavailable for 10-20 minutes to perform a storage cluster upgrade.
Published November 15, 2022 | Version v1
Journal article Open

CL2R: Compatible Lifelong Learning Representations

Description

In this article, we propose a method to partially mimic natural intelligence for the problem of lifelong learning representations that are compatible. We take the perspective of a learning agent that is interested in recognizing object instances in an open dynamic universe in a way in which any update to its internal feature representation does not render the features in the gallery unusable for visual search. We refer to this learning problem as Compatible Lifelong Learning Representations (CL2 R), as it considers compatible representation learning within the lifelong learning paradigm. We identify stationarity as the property that the feature representation is required to hold to achieve compatibility and propose a novel training procedure that encourages local and global stationarity on the learned representation. Due to stationarity, the statistical properties of the learned features do not change over time, making them interoperable with previously learned features. Extensive experiments on standard benchmark datasets show that our CL2 R training procedure outperforms alternative baselines and state-of-the-art methods. We also provide novel metrics to specifically evaluate compatible representation learning under catastrophic forgetting in various sequential learning tasks. Code is available at https://github.com/NiccoBiondi/CompatibleLifelongRepresentation.

Notes

This paper was published in ACM Trans. Multimedia Comput. Commun. Appl. 18, 2s, Article 132 (November 2022), 22 pages.

Files

CL2R_arxiv.pdf

Files (1.0 MB)

Name Size Download all
md5:8a331d2a254503410cb9b804e4116f59
1.0 MB Preview Download

Additional details

Funding

AI4Media – A European Excellence Centre for Media, Society and Democracy 951911
European Commission