Exploiting Spatial Correlation of Spectral Signature for Training Data Selection in Hyperspectral Image Classification

Appice, Annalisa; Guccione, Pietro

doi:10.1007/978-3-319-46307-0_19

Cited by 2 publications

(1 citation statement)

References 21 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Finally, both the unlabeled and labeled samples constitute the training set and used for network fine-tuning. Please note that we did not consider the spatial autocorrelation [65] of the input images during the process of separating training and testing samples. In addition, we organize samples in the form of 13 × 13 patches.…”

Section: Methodsmentioning

confidence: 99%

Superpixel-Guided Layer-Wise Embedding CNN for Remote Sensing Image Classification

Liu

et al. 2019

Remote Sensing

View full text Add to dashboard Cite

Irregular spatial dependency is one of the major characteristics of remote sensing images, which brings about challenges for classification tasks. Deep supervised models such as convolutional neural networks (CNNs) have shown great capacity for remote sensing image classification. However, they generally require a huge labeled training set for the fine tuning of a deep neural network. To handle the irregular spatial dependency of remote sensing images and mitigate the conflict between limited labeled samples and training demand, we design a superpixel-guided layer-wise embedding CNN (SLE-CNN) for remote sensing image classification, which can efficiently exploit the information from both labeled and unlabeled samples. With the superpixel-guided sampling strategy for unlabeled samples, we can achieve an automatic determination of the neighborhood covering for a spatial dependency system and thus adapting to real scenes of remote sensing images. In the designed network, two types of loss costs are combined for the training of CNN, i.e., supervised cross entropy and unsupervised reconstruction cost on both labeled and unlabeled samples, respectively. Our experimental results are conducted with three types of remote sensing data, including hyperspectral, multispectral, and synthetic aperture radar (SAR) images. The designed SLE-CNN achieves excellent classification performance in all cases with a limited labeled training set, suggesting its good potential for remote sensing image classification.

show abstract

Section: Methodsmentioning

confidence: 99%