Neural Stochastic Differential Equation for Hyperspectral Image Classification

Convolutional Neural Networks (CNNs) have been extensively applied to hyperspectral (HS) image classification tasks and achieved promising performance. However, for CNN based HS image classification methods, it is hard to depict the dependencies among HS image pixels in long-range distanced positions and bands. Moreover, the limited receptive field of the convolutional layers extremely hinders the development of the CNN structure. To tackle these problems, in this paper, the novel Bottleneck Spatial-Spectral Transformer (BS2T) is proposed to depict the long-range global dependencies of HS image pixels, which can be regarded as a feature extraction module for HS image classification networks. More specifically, inspired by Bottleneck Transformer in computer vision, for HS image feature extraction, the proposed BS2T is incorporated with a feature contraction module, a multi-head spatial-spectral self-attention (MHS2A) module and a feature expansion module. In this way, convolutional operations are replaced by the MHS2A to capture the long-range dependency of HS pixels regardless of their spatial position and distance. Meanwhile, in the MHS2A module, to highlight the spectral features of HS images, we introduce the spectral information and content spatial positional information to classical multi-head self-attentions to make the attentions more positional aware and spectral aware. On this basis, a dual-branch HS image classification framework based on 3D CNN and BS2T is defined for jointly extracting the local-global features of HS images. Experimental results on three public HS image classification datasets show that the proposed classification framework achieves a significant improvement when comparing with the state-of-the-art methods. The source code of the proposed framework can be downloaded from https://github.com/srxlnnu/BS2T.

Deep learning has achieved significant success in the field of hyperspectral image (HSI) classification, but challenges are still faced when the number of training samples is small. Feature fusing approaches based on multi-channel and multi-scale feature extractions are attractive for HSI classification where few samples are available. In this paper, based on feature fusion, we proposed a simple yet effective CNN-based Dual-channel Spectral Enhancement Network (DSEN) to fully exploit the features of the small labeled HSI samples for HSI classification. We worked with the observation that, in many HSI classification models, most of the incorrectly classified pixels of HSI are at the border of different classes, which is caused by feature obfuscation. Hence, in DSEN, we specially designed a spectral feature extraction channel to enhance the spectral feature representation of the specific pixel. Moreover, a spatial–spectral channel was designed using small convolution kernels to extract the spatial–spectral features of HSI. By adjusting the fusion proportion of the features extracted from the two channels, the expression of spectral features was enhanced in terms of the fused features for better HSI classification. The experimental results demonstrated that the overall accuracy (OA) of HSI classification using the proposed DSEN reached 69.47%, 80.54%, and 93.24% when only five training samples for each class were selected from the Indian Pines (IP), University of Pavia (UP), and Salinas Scene (SA) datasets, respectively. The performance improved when the number of training samples increased. Compared with several related methods, DSEN demonstrated superior performance in HSI classification.

With the continuous innovation in deep learning, it has become a major direction for scholars to introduce the knowledge of deep learning into hyperspectral image classification to enhance its classification accuracy. Convolutional Neural Networks (CNN) are one of the most commonly used deep learning-based visual data processing methods, and are widely used in hyperspectral image (HSI) classification by virtue of their excellent contextual modeling capability. Since the performance of HSI classification is highly dependent on spatial and spectral information, this paper proposes a hyperspectral image classification method using 3D attention mechanism in collaboration with Transformer for hyperspectral image classification in view of the problems that the current hyperspectral image classification models with the framework of CNN have insufficient spatial spectral feature extraction and fail to excavate and represent the sequence properties of spectral features well. In this paper, we introduce a variant Transformer model based on a hybrid model of both improved 3D-CNN and 2D-CNN, combining complementary information of spatial spectrum and spectra in the form of 3D convolution and 2D convolution on CNN, and adding a variant attention mechanism module to strengthen spatial texture features, while combining grouped transfer Transformer to jump connection to enable the lower layer to better learn the upper layer features. Firstly, a variant channel attention mechanism is introduced on 3D-CNN to enhance the acquisition of spectral information of image features by 3D-CNN. Secondly, a variant spatial attention mechanism is introduced to enable 3D-CNN to better acquire the spatial information of hyperspectral images in the network, and subsequently the acquired spatial and spectral feature information is passed to 2D-CNN to enable it to better acquire local feature information. Finally, the acquired image feature information is passed to the variant Transformer model to make up for the fact that CNN can only acquire hyperspectral image features in local contexts, enabling it to better acquire global feature information on feature sequences. The experimental results show that the proposed model is experimented on two hyperspectral datasets, Indian Pines and Pavia University, and the overall classification accuracy (OA), average classification accuracy (AA), and Kappa coefficient reach up to 99.59%, 99.31%, and 99.45%, respectively, on the PU dataset, compared with the current cutting-edge techniques. The classification accuracy has been improved.

Hyperspectral image (HSI) classification is one of the most popular applications in remote sensing. In practice, due to the high cost of manual labeling, only a few hyperspectral image samples with labels can be obtained. A small number of labeled training samples tend to overfit the deep network method, resulting in a sharp decline in classification accuracy. In order to solve this problem, this paper proposes a classification method for hyperspectral images based on knowledge distillation and heterogeneous few-shot learning. Firstly, the model pretrain the feature extraction network on miniImageNet, a small sample natural image dataset with abundant labeled images, and introduces knowledge distillation to improve the feature expression capability of shallow network in small sample. Then, effective knowledge transfer is carried out between two heterogeneous data sets, and the weights obtained from the model on the natural data set are transferred to the backbone network of hyperspectral image classification to improve the accuracy of HSI classification. Finally, the classifier is fine-tuned on HSI using the paradigm of small sample learning to extract discriminative hyperspectral image features and further enhance the model's detail expression. Experimental results on two hyperspectral image classification datasets show that the proposed method can effectively improve the accuracy of small sample hyperspectral image classification.

Hyperspectral image (HSI) classification has been a hot topic for decides, as hyperspectral images have rich spatial and spectral information and provide strong basis for distinguishing different land-cover objects. Benefiting from the development of deep learning technologies, deep learning based HSI classification methods have achieved promising performance. Recently, several neural architecture search (NAS) algorithms have been proposed for HSI classification, which further improve the accuracy of HSI classification to a new level. In this paper, NAS and Transformer are combined for handling HSI classification task for the first time. Compared with previous work, the proposed method has two main differences. First, we revisit the search spaces designed in previous HSI classification NAS methods and propose a novel hybrid search space, consisting of the space dominated cell and the spectrum dominated cell. Compared with search spaces proposed in previous works, the proposed hybrid search space is more aligned with the characteristic of HSI data, that is, HSIs have a relatively low spatial resolution and an extremely high spectral resolution. Second, to further improve the classification accuracy, we attempt to graft the emerging transformer module on the automatically designed convolutional neural network (CNN) to add global information to local region focused features learned by CNN. Experimental results on three public HSI datasets show that the proposed method achieves much better performance than comparison approaches, including manually designed network and NAS based HSI classification methods. Especially on the most recently captured dataset Houston University, overall accuracy is improved by nearly 6 percentage points. Code is available at: https://github.com/Cecilia-xue/HyT-NAS.

Over the past few decades, hyperspectral image (HSI) classification has garnered increasing attention from the remote sensing research community. The largest challenge faced by HSI classification is the high feature dimensions represented by the different HSI bands given the limited number of labeled samples. Deep learning and convolutional neural networks (CNNs), in particular, have been shown to be highly effective in several computer vision problems such as object detection and image classification. In terms of accuracy and computational cost, one of the best CNN architectures is the Inception model i.e., the winner of the ImageNet Large Scale Visual Recognition Competition (ILSVRC) 2014 challenge. Another architecture that has significantly improved image recognition performance is the Residual Network (ResNet) architecture i.e., the winner of the ILSVRC 2015 challenge. Inspired by the incredible performance introduced by the Inception and ResNet architectures, we investigate the possibility of combining the core ideas of these two models into a hybrid architecture to improve the HSI classification performance. We tested this combined model on four standard HSI datasets, and it shows competitive results compared with other existing HSI classification methods. Our hybrid deep ResNet-Inception architecture obtained accuracies of 95.31% on the Pavia University dataset, 99.02% on the Pavia Centre scenes dataset, 95.33% on the Salinas dataset and 90.57% on the Indian Pines dataset.

Hyperspectral image(HSI) Classification is one of the most prevalent issue in remote sensing area. Recently, application of deep learning in HSI classification has emerged. However, merging spatial features with spectral properties in deep learning is a pervasive problem. This paper presents, a discriminative spatial updated deep belief network (SDBN) which effectively utilizes spatial information within spectrally identical contiguous pixels for HSI classification. In the proposed approach, HSI is first segmented into adaptive boundary adjustment based spatially similar regions with similar spectral features, following which an object-level feature extraction and classification is undertaken using deep belief network (DBN) based decision fusion approach that incorporate spatial-segmented contextual and spectral information into a DBN framework for effective spectral-spatial HSI classification. Moreover, for improved accuracy, band preference/correlation based feature selection approach is used to select the most informative bands without compromising the original content in HSI. Usage of local contextual features and spectral similarity from adaptive boundary adjustment based approach, and integration of spatial and spectral features into DBN results into improved accuracy of the final HSI classification. Experimental results on well known hyperspectral data indicates the classification accuracy of the proposed method over several existing techniques.

Hyperspectral image classification based on discriminative locality preserving broad learning system

State space models meet transformers for hyperspectral image classification

Most hyperspectral image (HSI) classification methods assume that all classes in the test set are present during training. However, in real-world applications, acquiring labeled training samples is challenging. As a result, it is difficult for the training dataset to cover all possible land cover types, leading to the generalized zero-shot learning (GZSL) problem. Recently, vision-language models (VLMs) have provided rich semantic priors for land cover classes, offering promising potential for GZSL. However, two fundamental gaps hinder their application to HSI classification: the task paradigm gap, arising from the difference between image-level VLMs and the pixel-level HSI classification task; and the knowledge gap, due to the inconsistency between VLM features and HSI spectral–spatial representations. To bridge both gaps, a novel framework leveraging VLM semantic priors for GZSL in HSI classification is proposed, primarily using pseudo-labeling technique to provide knowledge for unseen classes. Specifically, a pseudo-label generation and enhancement module enables a paradigm transition from image-level understanding to pixel-level classification by incorporating HSI’s spatial information. A pseudo-label correction module then refines noisy labels using spectral cues to address the knowledge gap. Finally, a global learning strategy integrates pseudo-label distillation, supervised learning, and feature regularization to classify seen classes while enabling generalization to unseen ones. Experiments on benchmark HSI datasets demonstrate the proposed method’s superiority in generalized zero-shot classification. This work highlights the potential of VLMs in advancing HSI classification in practical applications.

A deep-learning-based feature extraction has recently been proposed for HyperSpectral Images (HSI) classification. A Deep Belief Network (DBN), as part of deep learning, has been used in HSI classification for deep and abstract feature extraction. However, DBN has to simultaneously deal with hundreds of features from the HSI hyper-cube, which results into complexity and leads to limited feature abstraction and performance in the presence of limited training data. Moreover, a dimensional-reduction-based solution to this issue results in the loss of valuable spectral information, thereby affecting classification performance. To address the issue, this paper presents a Spectral-Adaptive Segmented DBN (SAS-DBN) for spectral-spatial HSI classification that exploits the deep abstract features by segmenting the original spectral bands into small sets/groups of related spectral bands and processing each group separately by using local DBNs. Furthermore, spatial features are also incorporated by first applying hyper-segmentation on the HSI. These results improved data abstraction with reduced complexity and enhanced the performance of HSI classification. Local application of DBN-based feature extraction to each group of bands reduces the computational complexity and results in better feature extraction improving classification accuracy. In general, exploiting spectral features effectively through a segmented-DBN process and spatial features through hyper-segmentation and integration of spectral and spatial features for HSI classification has a major effect on the performance of HSI classification. Experimental evaluation of the proposed technique on well-known HSI standard data sets with different contexts and resolutions establishes the efficacy of the proposed techniques, wherein the results are comparable to several recently proposed HSI classification techniques.

Recently, Hyperspectral Image (HSI) classification methods based on deep learning models have shown encouraging performance. However, the limited numbers of training samples, as well as the mixed pixels due to low spatial resolution, have become major obstacles for HSI classification. To tackle these problems, we propose a resource-efficient HSI classification framework which introduces adaptive spectral unmixing into a 3D/2D dense network with early-exiting strategy. More specifically, on one hand, our framework uses a cascade of intermediate classifiers throughout the 3D/2D dense network that is trained end-to-end. The proposed 3D/2D dense network that integrates 3D convolutions with 2D convolutions is more capable of handling spectral-spatial features, while containing fewer parameters compared with the conventional 3D convolutions, and further boosts the network performance with limited training samples. On another hand, considering the existence of mixed pixels in HSI data, the pixels in HSI classification are divided into hard samples and easy samples. With the early-exiting strategy in these intermediate classifiers, the average accuracy can be improved by reducing the amount of computation cost for easy samples, thus focusing on classifying hard samples. Furthermore, for hard samples, an adaptive spectral unmixing method is proposed as a complementary source of information for classification, which brings considerable benefits to the final performance. Experimental results on four HSI benchmark datasets demonstrate that the proposed method can achieve better performance than state-of-the-art deep learning-based methods and other traditional HSI classification methods.

Graph neural networks (GNNs) have recently garnered significant attention due to their exceptional performance across various applications, including hyperspectral (HS) image classification. However, most existing GNN-based models for HS image classification are limited depth models and often suffer from performance degradation as model depth increases. This study introduces HyperGCN, an exclusive GNN-based model designed with multiple graph convolutional layers to exploit the rich spectral information inherent in HS images, thereby enhancing classification performance. To address performance degradation, HyperGCN incorporates techniques resistant to oversmoothing into its architecture. Additionally, multiple-side exit branches are integrated into the intermediate layers of HyperGCN, enabling dynamic management of the complexity of HS images. Less complex HS images are processed by fewer layers, exiting early via attached branches, while more complex images traverse multiple layers until reaching the final output layer. Extensive experiments on four benchmark HS datasets (Indian Pines, Pavia University, Salinas, and Botswana) demonstrate HyperGCN’s superior performance over basic GNN-based models. Notably, HyperGCN outperforms or performs comparably to the CNN-GNN combined model in classifying HS images. Furthermore, the superior performance of multi-exit HyperGCN over its single-exit counterpart emphasizes the effectiveness of incorporating side exit branches in GNN-based HS image classification. Compared to state-of-the-art models, multi-exit HyperGCN demonstrates competitive performance, highlighting its effectiveness in handling complex spectral information in HS images while maintaining an acceptable balance between accuracy and computational efficiency.

Hyperspectral image (HSI) classification has been one of the most important tasks in the remote sensing community over the last few decades. Due to the presence of highly correlated bands and limited training samples in HSI, discriminative feature extraction was challenging for traditional machine learning methods. Recently, deep learning based methods have been recognized as powerful feature extraction tool and have drawn a significant amount of attention in HSI classification. Among various deep learning models, convolutional neural networks (CNNs) have shown huge success and offered great potential to yield high performance in HSI classification. Motivated by this successful performance, this paper presents a systematic review of different CNN architectures for HSI classification and provides some future guidelines. To accomplish this, our study has taken a few important steps. First, we have focused on different CNN architectures, which are able to extract spectral, spatial, and joint spectral-spatial features. Then, many publications related to CNN based HSI classifications have been reviewed systematically. Further, a detailed comparative performance analysis has been presented between four CNN models namely 1D CNN, 2D CNN, 3D CNN, and feature fusion based CNN (FFCNN). Four benchmark HSI datasets have been used in our experiment for evaluating the performance. Finally, we concluded the paper with challenges on CNN based HSI classification and future guidelines that may help the researchers to work on HSI classification using CNN.

Deep convolutional neural networks (CNNs) have shown their outstanding performance in the hyperspectral image (HSI) classification. The success of CNN-based HSI classification relies on the availability sufficient training samples. However, the collection of training samples is expensive and time consuming. Besides, there are many pretrained models on large-scale data sets, which extract the general and discriminative features. The proper reusage of low-level and midlevel representations will significantly improve the HSI classification accuracy. The large-scale ImageNet data set has three channels, but HSI contains hundreds of channels. Therefore, there are several difficulties to simply adapt the pretrained models for the classification of HSIs. In this article, heterogeneous transfer learning for HSI classification is proposed. First, a mapping layer is used to handle the issue of having different numbers of channels. Then, the model architectures and weights of the CNN trained on the ImageNet data sets are used to initialize the model and weights of the HSI classification network. Finally, a well-designed neural network is used to perform the HSI classification task. Furthermore, attention mechanism is used to adjust the feature maps due to the difference between the heterogeneous data sets. Moreover, controlled random sampling is used as another training sample selection method to test the effectiveness of the proposed methods. Experimental results on four popular hyperspectral data sets with two training sample selection strategies show that the transferred CNN obtains better classification accuracy than that of state-of-the-art methods. In addition, the idea of heterogeneous transfer learning may open a new window for further research.