Revisiting the Transferability of Few-Shot Image Classification: A Frequency Spectrum Perspective

Revisiting the Transferability of Few-Shot Image Classification: A Frequency Spectrum Perspective

Few-shot learning, especially few-shot image classification (FSIC), endeavors to recognize new categories using only a handful of labeled images by transferring knowledge from a model trained on base categories. Despite numerous efforts to address the challenge of deficient transferability caused by...

Full description

Bibliographic Details
Main Authors: Min Zhang, Zhitao Wang, Donglin Wang
Format: Article
Language:English
Published: MDPI AG 2024-05-01
Series:Entropy
Subjects:
few-shot learning
few-shot image classification
frequency spectrum
distribution shift
causal perspective
Online Access:https://www.mdpi.com/1099-4300/26/6/473

Internet

https://www.mdpi.com/1099-4300/26/6/473

Similar Items