Search

Deep learning (DL) exhibits commendable performance in hyperspectral image (HSI) classification because of its powerful feature expression ability. Siamese neural network further improves the performance of DL models by learning similarities within-class and differences between-class from sample pairs. However, there are still some limitations in siamese neural network. On the one hand, siamese neural network usually needs a large number of negative pair samples in the training process, leading to computing overhead. On the other hand, current models may lack interpretability because of complex network structure. To overcome the above limitations, we propose a spectral-spatial siamese neural network with bag-of-features (S3BoF) for HSI classification. First, we use a siamese neural network with 3-D and 2-D convolutions to extract the spectral-spatial features. Second, we introduce stop-gradient operation and prediction head structure to make the siamese neural network work without negative pair samples, thus reducing the computational burden. Third, a bag-of-features (BoF) learning module is introduced to enhance the model interpretability and feature representation. Finally, a symmetric loss and a cross entropy loss are respectively used for contrastive learning and classification. Experiments results on four common hyperspectral datasets indicated that S3BoF performs better than the other traditional and state-of-the-art deep learning HSI classification methods in terms of classification accuracy and generalization performance, with improvements in terms of OA around 1.40%–30.01%, 0.27%–8.65%, 0.37%–6.27%, 0.22%–6.64% for Indian Pines, University of Pavia, Salinas, and Yellow River Delta datasets, respectively, under 5% labeled samples per class.

Convolutional neural network (CNN) has exhibited enormous potentials in hyperspectral image (HSI) classification owing to excellent locally modeling ability. Although excellent performance of CNN-based methods has been witnessed, there still have some limitations of their internal network backbone. On the one hand, modeling long-distance context dependencies is an inborn defect, which leads to receptive field limitation and insufficient feature capture in HSI. On the other hand, CNN-based methods usually need various sample distribution to train and cannot infer dynamically, which may not capture the inherent changes of HSI data well. To overcome the abovementioned issues, we propose a novel local transformer with spatial partition restore network (SPRLT-Net) for HSI classification. First, local transformer is introduced to obtain the spatial attention weights dynamically by measuring the similarity between related pixel pairs. Second, a spatial partition restore (SPR) module is designed to split the input patch into several overlapping continuous subpatches as sequential. With the obtained attention weights at hand, the SPR module restores the sequential to the original patch. Finally, a fully connected layer is used for classification. SPRLT-Net can capture global context dependencies, and the dynamical attention weights can adapt the inherent changes of HSI spatial pixels. Experimental results based on spatially disjoint samples and randomly selected samples of five benchmark datasets demonstrate that SPRLT-Net outperforms the other state-of-the-art methods in terms of classification accuracy, generalization performance, and computational complexity.

Deep learning (DL) have been intensively exploited for synthetic aperture radar (SAR) target classification, and we have witnessed exciting performances provided by previous studies. Multiview-based DL methods exhibited huge potentials for SAR target classification since they can generate adequate sample images from few raw images. In order to further improve the generalization performance of the multiview-based framework with limited training samples, we propose a novel multiview low-rank hybrid dilated network (MLHDN) for SAR target recognition. Firstly, we design a parameter-sharing hybrid dilated convolution (HDC) to learn multiview features. Secondly, a composite low-rank bilinear pooling (CLRBP) is proposed to fuse multiview features and to reduce their dimensions, yielding class-oriented and compacted feature vectors which are distinctive and representative for classification. Finally, a Softmax layer is used as a classifier. Accordingly, MLHDN encompasses fewer parameters compared to existing multiview-based DL methods. Experimental results demonstrate that MLHDN can achieve state-of-the-art performances on the moving and stationary target acquisition and recognition (MSTAR) datasets for SAR target classification, yielding an accuracy of 96.13% with only 10 training samples per class.

Tensor-based dimensionality reduction (DR) of hyperspectral images is a promising research topic. However, patch-based tensorization usually adopts a squared neighborhood with fixed window size, which may be inaccurate in modeling the local spatial information in a hyperspectral image scene. In this work, we propose a novel shape-adaptive tensor factorization (SATF) model for dimensionality reduction and classification of hyperspectral images. Firstly, shape-adaptive patch features are extracted to build fourth-order tensors. Secondly, multilinear singular value decomposition (MLSVD) is adopted for tensor factorization and latent features are extracted via mode-i tensor-matrix product. Finally, classification is conducted by using a sparse multinomial logistic regression (SMLR) model. Experimental results, conducted with two popular hyperspectral data sets collected over the Indian Pines and the University of Pavia, respectively, indicate that the proposed method outperforms the other traditional and tensor-based DR methods.