Affiliation:
1. University of Florence, Florence, Italy
Abstract
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
(CL
2
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 CL
2
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
.
Funder
European Horizon 2020 Programme
Publisher
Association for Computing Machinery (ACM)
Subject
Computer Networks and Communications,Hardware and Architecture
Reference80 articles.
1. Tommaso Barletti, Niccoló Biondi, Federico Pernici, Matteo Bruni, and Alberto Del Bimbo. 2022. Contrastive supervised distillation for continual representation learning. In Proceedings of the International Conference on Image Analysis and Processing. 597–609.
2. A comprehensive study of class incremental learning algorithms for visual tasks;Belouadah Eden;Neural Networks,2021
3. Representation learning: A review and new perspectives;Bengio Yoshua;IEEE Transactions on Pattern Analysis and Machine Intelligence,2013
4. CoReS: Compatible representations via stationarity;Biondi Niccolo;arXiv preprint arXiv:2111.07632,2021
5. Mateusz Budnik and Yannis Avrithis. 2021. Asymmetric metric learning for knowledge transfer. In Proceedings of the 2021 Conference on Computer Vision and Pattern Recognition (CVPR’21) . IEEE Los Alamitos CA 8228–8238.