Bayesian Learning-driven Prototypical Contrastive Loss for Class-Incremental Learning
The primary objective of methods in continual learning is to learn tasks in a sequential manner over time from a stream of data, while mitigating the detrimental phenomenon of catastrophic forgetting. In this paper, we focus on learning an optimal representation between previous class prototypes and...
Gespeichert in:
Hauptverfasser: | , , , , , |
---|---|
Format: | Artikel |
Sprache: | eng |
Schlagworte: | |
Online-Zugang: | Volltext bestellen |
Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
Zusammenfassung: | The primary objective of methods in continual learning is to learn tasks in a
sequential manner over time from a stream of data, while mitigating the
detrimental phenomenon of catastrophic forgetting. In this paper, we focus on
learning an optimal representation between previous class prototypes and newly
encountered ones. We propose a prototypical network with a Bayesian
learning-driven contrastive loss (BLCL) tailored specifically for
class-incremental learning scenarios. Therefore, we introduce a contrastive
loss that incorporates new classes into the latent representation by reducing
the intra-class distance and increasing the inter-class distance. Our approach
dynamically adapts the balance between the cross-entropy and contrastive loss
functions with a Bayesian learning technique. Empirical evaluations conducted
on both the CIFAR-10 and CIFAR-100 dataset for image classification and images
of a GNSS-based dataset for interference classification validate the efficacy
of our method, showcasing its superiority over existing state-of-the-art
approaches. |
---|---|
DOI: | 10.48550/arxiv.2405.11067 |