Incrementally Learned Angular Representations for Few-Shot Class-Incremental Learning

The main challenge of FSCIL is the trade-off between underfitting to a new session task and preventing forgetting the knowledge for earlier sessions. In this paper, we reveal that the angular space occupied by the features within the embedded area is relatively narrow. Consequently, after the base s...

Descripción completa

Detalles Bibliográficos

Autores principales:	In-Ug Yoon, Jong-Hwan Kim
Formato:	Artigo
Lenguaje:	Inglês
Publicado:	IEEE 2023-01-01
Colección:	IEEE Access
Materias:	Class-incremental learning few-shot learning few-shot class-incremental learning image classification
Acceso en línea:	https://ieeexplore.ieee.org/document/10353956/
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!