Weighted Contrastive Prototype Network for Few-Shot Hyperspectral Image Classification with Noisy Labels

Weighted Contrastive Prototype Network for Few-Shot Hyperspectral Image Classification with Noisy Labels

Few-shot hyperspectral image classification aims to develop the ability of classifying image pixels by using relatively few labeled pixels per class. However, due to the inaccuracy of the localization system and the bias of the ground survey, the potential noisy labels in the training data pose a ve...

Full description

Saved in:
Bibliographic Details
Main Authors: Dan Zhang, Yiyuan Ren, Chun Liu, Zhigang Han, Jiayao Wang
Format: Article
Language:English
Published: MDPI AG 2024-09-01
Series:Remote Sensing
Subjects:
hyperspectral image (HSI)
few-shot learning
prototype network
contrastive learning
noisy labels
Online Access:https://www.mdpi.com/2072-4292/16/18/3527
Tags: Add Tag
No Tags, Be the first to tag this record!

Internet

https://www.mdpi.com/2072-4292/16/18/3527

Similar Items