×
Sep 27, 2023 · A fully convolutional spectral–spatial fusion network based on supervised contrastive learning (FCSCL) is proposed for hyperspectral image classification.
To improve intra-class compactness and inter-class separability, the supervised contrastive learning module is integrated into the FCSCL framework. The positive ...
1) An FCSCL framework is proposed for hyperspectral im- age classification. The FCSCL framework integrates FCN and contrastive learning by sharing the feature ...
In the image classification pipeline, a spatial-spectral full convolution network (SSFCN) [26] is used as the classifier. The algorithm flow is shown in Fig. 3.
People also ask
May 14, 2024 · This survey provides a comprehensive overview of the current trends and future prospects in HSC, focusing on the advancements from DL models to the emerging ...
This paper presents a comprehensive review of GCN-based hyperspectral image classification methods. The review covers five aspects.
Missing: Fully Integrating
Find out what the research says about 'How does spatial-spectral feature fusion enhance hyperspectral image classification?'
Mar 16, 2023 · This study proposed a Transformer-based framework of spatial–spectral–associative contrastive learning classification methods to extract both spatial and ...
Mar 8, 2023 · To solve the small-sample classification problem, a deep contrastive learning network (DCLN) method is proposed in this paper.
Oct 10, 2024 · This study builds upon the previously established two-stage patch-level, multi-label classification method for hyperspectral remote sensing imagery.