Open-world continual learning: unifying novelty detection and continual learning

DOI10.1016/J.ARTINT.2024.104237MaRDI QIDQ6665718zbMATH OpenFDO

Authors Gyuhak Kim, Changnan Xiao, Tatsuya Konishi, Zixuan Ke, Bing Liu

Publication date 17 January 2025

Published in Artificial Intelligence (Search for Journal in Brave)

Full work available at URL https://doi.org/10.1016/J.ARTINT.2024.104237

zbMATH Keywords

continual learningOOD detectionopen world learning

Mathematics Subject Classification ID

Learning and adaptive systems in artificial intelligence (68T05)

Recommendations

• A comprehensive study of class incremental learning algorithms for visual tasks
• Dynamic Consolidation for Continual Learning
• Hierarchically structured task-agnostic continual learning
• Deep Bayesian unsupervised lifelong learning
• Class incremental learning with KL constraint and multi-strategy exemplar selection for classification based on MMFA model

Cites work

• Overcoming catastrophic forgetting in neural networks

This page was built for publication: Open-world continual learning: unifying novelty detection and continual learning

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6665718)