Prompt-based learning for few-shot class-incremental learning

Prompt-based learning for few-shot class-incremental learning

Few-Shot Class-Incremental Learning (FSCIL) aims to enable deep neural networks to incrementally learn new tasks from a limited number of labeled samples, while retaining knowledge of previously learned tasks, mimicking the way humans learn. In this paper, we introduce a novel approach called Prompt...

Full description

Bibliographic Details
Main Authors: Jicheng Yuan, Hang Chen, Songsong Tian, Wenfa Li, Lusi Li, Enhao Ning, Yugui Zhang
Format: Article
Language:English
Published: Elsevier 2025-05-01
Series:Alexandria Engineering Journal
Subjects:
Few-shot class-incremental learning
Prompt learning
Prototype classifier
Catastrophic forgetting
Online Access:http://www.sciencedirect.com/science/article/pii/S1110016825001735

Internet

http://www.sciencedirect.com/science/article/pii/S1110016825001735

Similar Items