Hard-Positive Prototypical Networks for Few-Shot Classification

Hard-Positive Prototypical Networks for Few-Shot Classification

Prominent prototype-based classification (PbC) approaches, such as Prototypical Networks (ProtoNet), use the average of samples within a class as the class prototype. In these methods which we call Mean-PbC, a discriminant classifier is defined based on the minimum Mahalanobis distance from class pr...

Description complète

Détails bibliographiques
Auteurs principaux: Mahsa Fazaeli-Javan, Reza Monsefi, Kamaledin Ghiasi-Shirazi
Format: Article
Langue:English
Publié: IEEE 2025-01-01
Collection:IEEE Access
Sujets:
Few-shot learning
hard-positive prototype
hard samples
Mahalanobis distance
prototype-based classification
Accès en ligne:https://ieeexplore.ieee.org/document/10900376/

Internet

https://ieeexplore.ieee.org/document/10900376/

Documents similaires