Latent spectral regularization for continual learning
Authors:
- Emanuele FrascaroliEFEmanuele Frascaroli
- Riccardo BenagliaRBRiccardo Benaglia
- Matteo BoschiniMatteo Boschini
- Luca MoschellaLMLuca Moschella
- Cosimo FioriniCFCosimo Fiorini
- Emanuele RodolàEmanuele Rodolà
- Simone CalderaraSCSimone Calderara
Open Access
- 22 June 2024
- journal article
- research article
- Published by Elsevier in Pattern Recognition Letters
- Vol. 184, 119-125
Abstract
No abstract availableKeywords
All Related Versions
Funding Information
- Ministero dell'Istruzione dell'Universita e della Ricerca
This publication has 11 references indexed in Scilit:
- Three types of incremental learningNature Machine Intelligence, 2022
- Learning Spectral Unions of Partial Deformable 3D ShapesComputer Graphics Forum, 2022
- Supervised Contrastive Replay: Revisiting the Nearest Class Mean Classifier in Online Class-Incremental Continual Learning2021
- A continual learning survey: Defying forgetting in classification tasksIEEE Transactions on Pattern Analysis and Machine Intelligence, 2021
- The Riemannian Geometry of Deep Generative Models2018
- Overcoming catastrophic forgetting in neural networksProceedings of the National Academy of Sciences, 2017
- Multiway Spectral Partitioning and Higher-Order Cheeger InequalitiesJournal of the ACM, 2014
- Functional mapsACM Transactions on Graphics, 2012
- Approximate counting, uniform generation and rapidly mixing Markov chainsInformation and Computation, 1989
- Catastrophic Interference in Connectionist Networks: The Sequential Learning Problem1989