Spectral-Spatial Classification of Hyperspectral Images Using BERT-Based Methods With HyperSLIC Segment Embeddings

Spectral-Spatial Classification of Hyperspectral Images Using BERT-Based Methods With HyperSLIC Segment Embeddings

The classification performance is highly affected because hyperspectral images include many bands, have high dimensions, and have few labeled training samples. This challenge is reduced by using rich spatial information and an effective classifier. The classifiers in this study are BERT-based (Bidir...

Full description

Bibliographic Details
Main Authors: Ibrahim Onur Sigirci, Gokhan Bilgin
Format: Article
Language:English
Published: IEEE 2022-01-01
Series:IEEE Access
Subjects:
ALBERT
BERT
classification
hyperspectral images
hyperSLIC
segmentation
Online Access:https://ieeexplore.ieee.org/document/9843967/

Internet

https://ieeexplore.ieee.org/document/9843967/

Similar Items