Active learning-clustering-group convolutions network for hyperspectral images classification
Information Sciences|更新时间:2024-05-18
|
Active learning-clustering-group convolutions network for hyperspectral images classification
“Technology News Broadcast: In the field of hyperspectral image classification, experts have proposed an innovative method AL CGNet. This method combines active learning and clustering grouping networks to effectively address the challenges of large network parameters and few labeled samples. AL CGNet reduces the number of parameters through a lightweight network model and improves classification accuracy by utilizing unlabeled sample information. Experimental results have shown that AL CGNet performs well on multiple datasets, significantly improving the efficiency and accuracy of HSI classification, providing strong support for research in related fields.”
Optics and Precision EngineeringVol. 32, Issue 9, Pages: 1395-1407(2024)
LIU Jing,LI Yinqiao,LIU Yi.Active learning-clustering-group convolutions network for hyperspectral images classification[J].Optics and Precision Engineering,2024,32(09):1395-1407.