A Coarse-to-Fine Semi-supervised Learning Method Based on Superpixel Graph and Breaking-tie Sampling for Hyperspectral Image Classification

At present, hyperspectral image classification (HSIC) technology based on deep learning has been widely explored. However, the time and labor cost of obtaining enough labeled samples are expensive. To obtain higher classification performance with a few number of labeled samples, a coarse-to-fine sem...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:IEEE geoscience and remote sensing letters 2023-07, p.1-1
Hauptverfasser: Zhao, Chunhui, Chen, Maoyang, Feng, Shou, Qin, Boao, Zhang, Lifu
Format: Artikel
Sprache:eng
Schlagworte:
Online-Zugang:Volltext bestellen
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung:At present, hyperspectral image classification (HSIC) technology based on deep learning has been widely explored. However, the time and labor cost of obtaining enough labeled samples are expensive. To obtain higher classification performance with a few number of labeled samples, a coarse-to-fine semi-supervised classification learning (CFSSL) method is proposed in this letter. First of all, the CFSSL performs coarse-grained classification with a few number of labeled samples, and the breaking-ties (BT) criterion is introduced to sample the coarse-grained classification results to ensure that the samples with high confidence are selected to generate pseudo-labels. Then, the pseudo-labels and their corresponding unlabeled samples are sent to the feature extraction network for fine-grained classification, so as to obtain more advanced classification results. Finally, in the fine-grained classification stage, a multi-scale convolution kernel attention aggregation network ( A 2 -MCKN) is designed to simultaneously extract the spatial-spectral features of the image and ensure clear texture boundaries of ground objects. Experimental results on two public datasets show that the CFSSL can obtain better accuracy than other methods with a few number of labeled samples.
ISSN:1545-598X
DOI:10.1109/LGRS.2023.3297110