Unified Probabilistic Deep Continual Learning through Generative Replay and Open Set Recognition

Unified Probabilistic Deep Continual Learning through Generative Replay and Open Set Recognition

Modern deep neural networks are well known to be brittle in the face of unknown data instances and recognition of the latter remains a challenge. Although it is inevitable for continual-learning systems to encounter such unseen concepts, the corresponding literature appears to nonetheless focus prim...

Full description

Bibliographic Details
Main Authors: Martin Mundt, Iuliia Pliushch, Sagnik Majumder, Yongwon Hong, Visvanathan Ramesh
Format: Article
Language:English
Published: MDPI AG 2022-03-01
Series:Journal of Imaging
Subjects:
continual deep learning
catastrophic forgetting
open-set recognition
variational inference
deep generative models
Online Access:https://www.mdpi.com/2313-433X/8/4/93

Internet

https://www.mdpi.com/2313-433X/8/4/93

Similar Items