Underwater image enhancement (UIE) aims to address image degradation caused by water absorption and scattering effects. Despite significant progress in deep learning-based UIE methods, existing approaches still face key challenges due to the neglect of physical imaging principle. Moreover, while current Mamba models achieve global modeling via multi-directional scanning, their local sequential strategy lacks sufficient global context. To this end, we propose a novel Physical Model-Guided Global Mamba (PGMamba) that combines the efficient sequential modeling capability of Mamba with underwater imaging physical model. Specifically, we first design a Spatial-Aware Global Mamba (SAGMamba) that achieves efficient long-range dependency modeling through a spatial-aware ranking strategy with global context information. Second, we develop a Physical Model-Guided Feed-Forward Network (PMGFFN) that explicitly incorporates underwater optical imaging principles into the network architecture. Extensive experimental results and comprehensive ablation studies demonstrate the outstanding performance and importance of our proposed method.

Hyperspectral image (HSI) reconstruction refers to the process of recovering the high-dimensional HSI signal from the measurements captured by various imaging systems. In the case of the coded aperture snapshot spectral imaging (CASSI) system, this involves recovering the HSI signal from snapshot measurements obtained using a coded aperture and disperser. However, previous methods for HSI reconstruction have been limited by the challenges of reconstructing complex high-dimensional data and the inevitable noise present in the measurements. To better capture the complex distribution of high-dimensional data and mitigate the impact of noise on reconstruction performance, this paper introduces an end-to-end approach leveraging a diffusion model, termed the hierarchically conditional diffusion model for HSI reconstruction (HDiff-HIR). HDiff-HIR achieves high-quality reconstruction by initializing with pure Gaussian noise and using a network to iteratively refine it. Additionally, we design a condition generation module, called the mask-integrated condition generation module (MCGM), which integrates 2D measurements with the coded aperture of the imaging system as conditions and hierarchically embeds them into the denoising network. Furthermore, within the network, we introduce a novel self-attention mechanism, named local-global spectral-enhanced multi-head self-attention (LGS-MSA), to efficiently capture long-range spatial dependencies in HSIs at relatively modest computational costs while incorporating fine-grained spectral features as complementary information. In LGS-MSA, we incorporate time embeddings to make it time-dependent, enabling it to capture both long-range spatial and temporal dependencies simultaneously. Through comprehensive experiments on both simulated and real datasets, we demonstrate that HDiff-HIR not only outperforms other advanced methods but also exhibits strong generalization capability. The code of HDiff-HIR is accessible: https://github.com/chenx2000/HDiff-HIR.

Multi-temporal hyperspectral imagery (HSI) has become a powerful tool for change detection (CD) owing to its rich spectral signatures and detailed spatial information. Nevertheless, the application of paired HSIs is constrained by the scarcity of annotated training data. While unsupervised domain adaptation (UDA) offers a potential solution by transferring change detection knowledge from source to target domains, two critical limitations persist: 1) the labor-intensive process of acquiring and annotating source-domain paired samples, and 2) the suboptimal transfer performance caused by substantial cross-domain distribution discrepancies. To address these challenges, we present a Temporal Self-Construction Cross-Domain learning (TSCCD) framework for UDA-based HSI-CD. Our TSCCD framework introduces an innovative temporal self-construction mechanism that synthesizes bi-temporal source-domain data from existing HSI classification datasets while simultaneously performing initial data-level alignment. Furthermore, we develop a reweighted amplitude maximum mean discrepancy (MMD) metric to enhance feature-level domain adaptation. The proposed architecture incorporates an attention-based Kolmogorov-Arnold network (KAN) with high-frequency feature augmentation within an encoder-decoder structure to effectively capture change characteristics. Comprehensive experiments conducted on three benchmark HSI datasets demonstrate that TSCCD achieves superior performance compared to current state-of-the-art methods in HSI change detection tasks. Codes are available at https://github.com/Zhoutya/TSCCD.

The high spectral resolution of the hyperspectral image (HSI) has facilitated the wide applications of anomaly detection techniques. However, existing HSI anomaly detection (HAD) methods usually deal with HSIs as a 2-D matrix and violate their inherent 3-D structures. Also, the limited spatial resolution often leads to intricate background-anomaly mixed subpixels, which makes accurate background learning and anomaly detection a challenge. To address the issues, this letter proposes to fully explore the inherent 3-D structural properties of HSIs and develop a coarse-to-fine tensor two-level decomposition (CTTD) method for HAD. Specifically, the primary decomposition is performed via tensor robust principal component analysis (TRPCA), to simultaneously discover the global tensor background component and the coarse group sparse anomaly component of HSIs. Then, the secondary decomposition with joint$\ell _{2,1,1}$and weighted nuclear norms (WNNs) is devised with the obtained global tensor background component in primary decomposition, to pursue the refined 3-D spatial-spectral sparse anomaly component. Finally, with the coarse-to-fine background learning and anomaly detection mechanism, the informative anomaly cues from the coarse group sparse and refined 3-D spatial-spectral sparse anomaly components are enhanced by weighted fusion, to achieve the final accurate detection result. Extensive experiments on various real-world HSI datasets verify the superior performance of our proposed CTTD than some state-of-the-art HAD methods.

Classification methods based on subgraph neural networks (SNNs) are rarely explored, and its advantage is that it can alleviate the neighbor explosion problem. After applying SNNs to hyperspectral image (HSI) classification, the imbalanced topology structure in the internal subgraph leads to poor classification performance due to the intraclass and interclass spectral feature variation. Based on this, we proposed a novel subgraph-dependent neural network (SGDNet) for HSI classification. Specifically, we firstly segmented the large graph to a series of subgraphs, and proposed a subgraph-dependent convolution method for imbalanced subgraph structure to achieve effective feature smoothing within each subgraph. It mainly utilized the degree feature embedding with the residual to improve the feature diversity as well as the intraclass distance of clustering measurement to determine the optimal subgraph convolution layers in a feedback way. Secondly, we developed the strategy of the long-range dependency to address the inevitably local structure dependence among nodes within subgraphs. It utilized an anchor point based position coding method to capture the relative positions of unlabeled nodes in relation to all labeled nodes within the graph and further constructed the structural loss function for effective training, achieving subgraph optimization. Comprehensive experiments demonstrated the superior performance of the SGDNet model on three publicly available HSI datasets, compared to other popular methods. The source code will be available at https://github.com/lichao226211/SGDNet.

Recently, hypergraph convolution networks (HGCNs) have shown considerable potential in hyperspectral image (HSI) classification for their superiority in capturing the complex many-to-many structure among multiple ground object samples. However, the absence of high-order pooling operation for many-to-many structure restricts networks to shallow architectures, limiting extracting deep discriminative features. To break this limitation, we propose a clustering hypergraph U-net (CHGUnet) incorporating high-order topology-aware pooling and unpooling operations. Specifically, a sparse fuzzy clustering strategy is first designed to explore multivariate relationships among multiple superpixels of ground objects, thereby building the high-order topological association hypergraph for hierarchical hypergraph convolution in the U-Net architecture. Meanwhile, the hypergraph pooling and unpooling (HGPool and HGUnPool), designed with high-order topology-aware assessments on both views of node and hyperedge, are adapted for adjusting high-order topological association to learn more suitable structured features that are beneficial to classification. Finally, a lightweight depth separable convolution branch is integrated into the network through cross-level interactive fusion mechanism, enhancing the superpixel-level features derived from hypergraph convolution with complementary pixel-level details. Such a CHGUnet can learn comprehensive discriminative features from high-order topological perspective, and the experiments on three HSI data sets have proven its competitive performance in contrast to other advanced methods.

Infrared small target detection (IRSTD) faces significant challenges due to low signal-to-noise ratios, poor contrast in infrared images, and the tendency for small and dim targets to be obscured by cluttered backgrounds. These factors complicate the extraction of diverse and effective information for target detection, with existing encoder-decoder architectures often causing irreversible loss of small target features through continuous down-sampling, resulting in missed and false detections. To address these challenges, we propose the Diverse Feature Capture and Harmonization Network (DFCHNet), which learns and harmonizes diverse features through multiple encoding paths. DFCHNet includes an infrared image reconstruction branch running in parallel with the detection branch, preserving small target information and reducing feature loss via complementary contextual encoding. Additionally, we introduce FTConv to capture target edges while suppressing background noise. A Cross-layer Feature Autonomous Selection (CFAS) method adaptively harmonizes cross-layer features. We also propose a Coordinate Calibration (CC) loss function and a two-stage training strategy to refine predicted target positions. Experimental results on three IRSTD datasets demonstrate that DFCHNet outperforms current state-of-the-art methods.

Deep learning has shown great potential in hyperspectral image (HSI) classification. However, training these models usually requires a large amount of labeled data. Since the collection of pixel-level annotations for HSIs is laborious and time-consuming, developing algorithms that can yield good performance in a small sample size situation is of great significance. Therefore, many research works focus on building a deep learning model for HSI classification with few labeled samples. However, prevalent solutions are unsatisfactory in feature discrimination and model overfitting, which greatly limits their performance. To remedy these drawbacks, we propose a novel spatial-spectral enhancement and fusion network for hyperspectral image classification with few labeled samples, named SSEFN. Specifically, we design a spatial-spectral enhancement strategy (SSES) to boost the feature discrimination from spatial and spectral perspectives, which enables the model to learn more easily with fewer samples. In addition, we propose an adaptive decision fusion (ADF) module to fuse the decisions of all enhanced features. Since each decision prediction may have a different trend of overfitting, combining multiple predictions alleviates the overfitting. Extensive experiments are conducted on four diverse hyperspectral image datasets. The results show that our method significantly outperforms the state-of-the-art approaches on all datasets and demonstrates the effectiveness and superiority of the proposed model for hyperspectral image classification with few labeled samples. Codes are available athttps://github.com/liushuang963/SSEFN.

Recently, semi-supervised change detection (SSCD) has attracted considerable attention due to its remarkable capability to enhance model performance with limited annotated data. However, most existing SSCD methods rely primarily on pixel-level consistency learning to leverage unlabeled data. Although this approach can provide basic prediction consistency constraints, it exhibits notable limitations in capturing spatial continuity and global semantic coherence in structural change regions, and is easily affected by noise. To address this issue, we propose a novel SSCD framework, termed the local-global tri-consistency network (LGTC). LGTC incorporates a tri-consistency learning strategy at the pixel, region, and image levels, which provides complementary supervisory signals from fine-grained to global semantic scales, significantly enhancing representation ability and robustness on unlabeled data. Furthermore, a local-global interaction block (LGIBlock) is introduced to integrate local feature details with global context. Within it, the GFTBlock employs frequency domain attention to achieve efficient modeling of global information while effectively suppressing background noise, further enhancing the recognition performance of the model. Experimental results demonstrate that LGTC achieves state-of-the-art performance, attaining F1 scores of 87.12%, 88.65% and 83.25% on the LEVIR-CD, WHU-CD and CDD-CD dataset with 5% labeled data, respectively, fully verifying the effectiveness of the proposed method. Our source codes are available at https://github.com/sherryxu21/LGTC.

Hyperspectral images (HSIs) are rich in spectral information and are widely used in the field of land-cover classification. However, existing deep learning methods ignore the combination of multiscale and multiresolution information, while not making better use of light detection and ranging (LiDAR) elevation information to assist in the enhancement of HSI data. To solve the problem above, we proposed a multiresolution, multiscale local-global directional MLP (MMD-MLP) for HSI classification with a LiDAR-guided feature enhancement module in this article. The algorithm first introduced a local-global-directed MLP structure, which effectively combines local and global features. Second, a multiresolution and multiscale feature extraction strategy is invented for the accurate acquisition of the detailed information and features of different land covers under different scale sizes. Subsequently, a LiDAR-guided feature enhancement module, which introduces the elevation information from LiDAR for improving the feature representation of HSI, adopts a cross-attention mechanism to reduce the semantic gap to improve the features of HSI. The proposed algorithm was evaluated on multiple hyperspectral-LiDAR datasets, and the results demonstrate that it achieves state-of-the-art (SOTA) performance. The code will be available athttps://github.com/sanxian-svg/MMD-MLP.

Cross-view consensus representation plays a crucial role in hyperspectral image (HSI) clustering. Recently, multi-view contrastive cluster (MVCC) methods have leveraged contrastive loss to extract contextual consensus representations. However, these methods suffer from a critical limitation: MVCC frameworks often regard similar heterogeneous views as positive sample pairs while treating dissimilar homogeneous views as negative sample pairs. This misalignment leads to intra-class inconsistency and inter-class confusion. To address this problem, we propose a novel multi-view clustering method, termed Semantic Constraint-based Spatial-Spectral Multi-view Clustering (SCMVC). First, spatial views are designed to capture diverse features for contrastive clustering. Meanwhile, globally relevant information from the spectral view is extracted using a Transformer, which serves to enhance the representation of similar samples in the spatial multi-view. Then, SCMVC employs a semantic constraint-based joint loss function, comprising a semantic contrast loss and a semantic similarity consistency loss. The semantic contrast loss captures high-level, domain-invariant features from hyperspectral images, while the semantic similarity consistency loss enforces stricter constraints on the similarity of semantically related samples in feature space. Finally, SCMVC utilizes anchor points to guide similarity clustering, reducing randomness by predefining these points. This approach captures the directional characteristics of data, leading to a more stable clustering process. Abundant experiment studies on numerous benchmarks verify the superiority of SCMVC in comparison to some state-of-the-art clustering methods. The codes are available at SCMVC.

Hyperspectral target detection (HTD) is an approach to identify targets of interest in a scene by utilizing prior target spectra. Existing deep learning-based HTD methods usually need to generate a large number of samples for network training, and these generated samples often suffer from distortion. In addition, most of the methods can only be applied to a single scene. To address these issues, this study proposes a self-supervised meta-transfer learning (SelfMTL) method to improve the generalization ability and adaptability of the model through contrastive representation. First, labeled source data, which contains rich feature information, is utilized to train the global-local spectral contrastive learning (GLSL) module by randomly constructing positive and negative pairs from different land covers for the classification task, aiming to effectively discriminate the similarities and differences between spectra. Then, a small sample (only one target-background pair) fine-tuning is utilized to transfer the pretrained GLSL to different target detection (TD) tasks. Finally, a novel adaptive spatial-spectral enhancement (ASSE) module is proposed, which takes into account the joint learning constraints of spatial and spectral information to obtain the final detection result map. The experimental results on four real hyperspectral images (HSIs) datasets verify the superiority of SelfMTL in comparison to many classical and SOTA HTD methods. The codes are available athttps://github.com/ShissHAN/SelfMTL.

Change detection (CD) is one of the prominent research topics in the fields of Earth science and remote sensing. Recently, an increasing number of deep learning-based CD methods have been developed. Most of the current CD methods require lots of pixel-level labels for supervised learning. However, annotating all the changed pixels in bitemporal images is both challenging and time-consuming. In this work, as a first attempt in the field of CD, we propose a novel CD framework, similarity-awareness weakly supervised CD (SWCD) to achieve accurate CD, which uses weakly supervised learning as an auxiliary task to guide the model in both semi-supervised and supervised learning. In the weakly supervised branch (WSB), we incorporate the concept of similarity and introduce similarity information into the supervised branch to guide pixel-level CD learning, thus enhancing feature continuity. Moreover, large kernel convolution attention is introduced to enhance multiscale feature learning. In the supervised branch, we re-evaluate the approach to multiscale feature aggregation and introduce an adaptive feature module to integrate features from both global and local perspectives. Furthermore, our method can serve as a general framework that is compatible with the existing CD approaches. Experimental results on four CD datasets demonstrate the superior effectiveness and generalization of our proposed method. The code is available athttps://github.com/ZijunTan/SWCD.

Due to the powerful feature extraction capabilities of deep learning, a series of deep learning-based methods for hyperspectral image (HSI) classification have been proposed and achieved satisfactory performance. However, most of these methods require a large number of labeled data, and the collection of completely accurate pixel-level labeled HSI data is difficult, resulting from the intricate label ambiguity of HSI and incomplete prior knowledge of annotators. Simultaneously, a few researchers focus on label ambiguity for HSI classification. Partial label learning (PLL) is one of the strategies to solve the problem where each training instance is assigned a candidate label set, among which only one is the ground truth label, which can essentially alleviate labeling difficulties. In this article, a max-gap loss-guided Siamese reconstruction network (MAGS) is proposed to combine PLL with HSI classification. MAGS consists of three components, including a spatial-spectral encoder, a spatial-spectral decoder, and a Siamese spatial-spectral encoder for high-quality feature representation learning to facilitate label disambiguation. In the encoding process, MAGS introduces the cross-attention and max-matching fusion strategies to obtain more representative features. In addition, to improve label disambiguation, the maximum gap loss is designed to guide the model training. Quantitative and qualitative results indicate that the MAGS outperforms several state-of-the-art methods on three HSI datasets. The code is available athttps://github.com/Nemo96yu/MAGS.

Multitemporal hyperspectral images (HSIs) have been widely applied in change detection (CD) of different land covers for their rich spectral features and image details. However, alignment and labeling pairs of bitemporal HSIs are labor-intensive. In this article, we propose a single-temporal mask-based network (STMNet) for self-supervised HSI CD from a new perspective of detecting masks as changes. STMNet implements self-supervised by treating artificially constructed masks attached to single-temporal HSI as changed regions. To this end, we design a multiscale mask change simulation (MMCS) strategy to generate pseudo-second-temporal HSI closer to the real case. Meanwhile, a global-local feature aggregation network is proposed to enhance long-distance and local spatial-spectral feature extraction. To the best of our knowledge, this is the first work in the field of HSI CD that uses single-temporal HSIs and eliminates the need for labeling and pairing samples, alleviating the problem of difficult multitemporal HSI annotation. The visual and quantitative experimental results on three HSI datasets show that the proposed STMNet outperforms the compared state-of-the-art methods for HSI CD. Codes are available athttps://github.com/Zhoutya/ChangeDetection-STMNet.

Snapshot compressive imaging (SCI) compresses a 3D hyperspectral image (HSI) into a 2D measurement, significantly improving imaging efficiency while preserving the spatial and spectral information inherent in HSI. However, reconstructing high-quality HSIs from compressed measurements remains a core challenge due to the complexity of the inverse problem. Transformer-based methods have recently shown promising performance in HSI reconstruction. Nonetheless, effectively capturing local information, long-range dependencies, and multi-scale features within a reasonable computational cost remains a significant challenge. In this paper, we propose a dual-stage multiscale Transformer (DSMT) tailored for HSI reconstruction, which adopts a coarse-to-fine framework to enhance reconstruction accuracy and network generalization. Specifically, we design a novel U-Net architecture with a dual-branch encoder, where two separate branches process distinct features and are fused to achieve more refined reconstruction results. Full-scale skip connections are introduced to strengthen feature fusion across different stages. To further improve performance, we develop a novel self-attention mechanism called dual-window multiscale multi-head self-attention (DWM-MSA). By utilizing two differently sized windows, DWM-MSA captures long-range dependencies and local information at multiple scales, significantly boosting reconstruction quality. Additionally, we introduce a hybrid positional embedding method, conditional/relative positional embedding (CRPE), which dynamically models both spatial and spectral dependencies, effectively enhancing the Transformer's capacity for HSI reconstruction. Extensive quantitative and qualitative experiments on both the simulated and the real data are conducted to demonstrate the superior performance, stability, and generalization ability of our DSMT. Code of this project is at https://github.com/chenx2000/DSMT.

Automatic road extraction from high-resolution remote sensing images has greatly facilitated the applications of high-precision road mapping in autonomous driving and intelligent transportation. However, challenges such as occlusions from buildings, trees, and complex road shapes bring great difficulties to precise road extraction. Also, existing methods often overlook the integrity of road direction and edge, leading to unsatisfactory extraction results. To alleviate the issue, this paper has presented a direction and edge co-awareness network (DENet). Firstly, the road edge detector (RED) is introduced to extract coarse road edges with abundant directional information. By leveraging the edge enhancement blocks, the edge structures of road can be efficiently refined, achieving the extraction of intricate narrow and elongated road shapes. Secondly, we incorporate the directional spatial attention (DSA) mechanism within the dual encoders and decoders to promote the extraction and fusion of road directional information and elongated features from different orientations, thus greatly mitigating the road occlusion issue. Finally, to fully interlace potential road information, a grouped local-global feature fusion (GLFF) is specifically designed to exchange multi-scale semantic information across different channels, simultaneously emphasizing road features and suppressing irrelevant background features. Numerous experimental results on three public datasets demonstrate the effectiveness and efficiency of the proposed DENet for road extraction, achieving F1 scores of 78.51% on the CHN6-CUG dataset, 79.35% on the Massachusetts road dataset, and 77.90% on the GF2-FC dataset, outperforming several existing state-of-the-art methods. The code is available at:https://github.com/gwy103/DENet.

The emerging federated learning enables distributed autonomous vehicles to train equipped deep learning models collaboratively without exposing their raw data, providing great potential for utilizing explosively growing autonomous driving data. However, considering the complicated traffic environments and driving scenarios, deploying federated learning for autonomous vehicles is inevitably challenged by non-independent and identically distributed (Non-IID) data of vehicles, which may lead to failed convergence and low training accuracy. In this paper, we propose a novel hierarchically Federated Region-learning framework of Autonomous Vehicles (FedRAV) that adaptively divides a large area containing vehicles into sub-regions based on the defined region-wise distance, and achieves personalized vehicular models and regional models. Specifically, the architecture employs a designated hypernetwork to learn personalized mask vectors per vehicle used in the linear combination of models shared by vehicles in the same region. This approach ensures that the updated vehicular model adopts the beneficial models while discarding the unprofitable ones. We validate our FedRAV framework against existing federated learning algorithms on four real-world autonomous driving datasets in various heterogeneous settings. Extensive experiment results demonstrate that FedRAV framework achieves superior performance than the state-of-the-art algorithms, and improves the accuracy by 9.36%. The source code of FedRAV is available at:https://github.com/yjzhai-cs/FedRAV.

Group convolution networks have shown great potential in hyperspectral image (HSI) classification because of their ability to divide total spectral bands into multiple groups and focus on fine discrimination within different spectral ranges. Most group convolution networks process parallel spectral groups independently; however, they neglect the important relevance of nearby spectral ranges. Moreover, the feature maps from different spectral groups are not considered for recalibration in the existing attention. To address these issues, we propose a novel group interactive threshold attention network (GITANet). In the network, a stratified-split-concatenation strategy, which not only splits all bands into multiple groups for intragroup convolution but also propagates the intergroup information via the stratified concatenation operation between different groups, is designed for bandwise group convolution. Relying on the high dependencies among nearby spectra, the cross-group interactive attention block is designed to encourage significant spectral features. Subsequently, from different spectral ranges, a learnable threshold generation block is built to estimate the information validity of each pixel. On the basis of this threshold, soft threshold spatial attention is developed in the bandwise encoder-decoder architecture, which emphasizes high-value spatial areas during the fusion of group convolutional features. Therefore, complementary and discriminative spectral-spatial features are obtained to improve the performance of HSI classification. The experimental results on three HSI datasets illustrate that GITANet is superior to several state-of-the-art networks.

Coded aperture snapshot spectral imaging (CASSI) system is an effective manner for hyperspectral snapshot compressive imaging. The core issue of CASSI is to solve the inverse problem for the reconstruction of hyperspectral image (HSI). In recent years, Transformer-based methods achieve promising performance in HSI reconstruction. However, capturing both long-range dependencies and local information while ensuring reasonable computational costs remains a challenging problem. In this paper, we propose a Transformer-based HSI reconstruction method called dual-window multiscale Transformer (DWMT), which is a coarse-to-fine process, reconstructing the global properties of HSI with the long-range dependencies. In our method, we propose a novel U-Net architecture using a dual-branch encoder to refine pixel information and full-scale skip connections to fuse different features, enhancing the extraction of fine-grained features. Meanwhile, we design a novel self-attention mechanism called dual-window multiscale multi-head self-attention (DWM-MSA), which utilizes two different-sized windows to compute self-attention, which can capture the long-range dependencies in a local region at different scales to improve the reconstruction performance. We also propose a novel position embedding method for Transformer, named con-abs position embedding (CAPE), which effectively enhances positional information of the HSIs. Extensive experiments on both the simulated and the real data are conducted to demonstrate the superior performance, stability, and generalization ability of our DWMT. Code of this project is at https://github.com/chenx2000/DWMT.

Cross-view consensus representation plays a critical role in hyperspectral images (HSIs) clustering. Recent multi-view contrastive cluster methods utilize contrastive loss to extract contextual consensus representation. However, these methods have a fatal flaw: contrastive learning may treat similar heterogeneous views as positive sample pairs and dissimilar homogeneous views as negative sample pairs. At the same time, the data representation via self-supervised contrastive loss is not specifically designed for clustering. Thus, to tackle this challenge, we propose a novel multi-view clustering method, i.e., Enhanced Multi-View Contrastive Clustering (EMVCC). First, the spatial multi-view is designed to learn the diverse features for contrastive clustering, and the globally relevant information of spectrum-view is extracted by Transformer, enhancing the spatial multi-view differences between neighboring samples. Then, a joint self-supervised loss is designed to constrain the consensus representation from different perspectives to efficiently avoid false negative pairs. Specifically, to preserve the diversity of multi-view information, the features are enhanced by using probabilistic contrastive loss, and the data is projected into a semantic representation space, ensuring that the similar samples in this space are closer in distance. Finally, we design a novel clustering loss that aligns the view feature representation with high confidence pseudo-labels for promoting the network to learn cluster-friendly features. In the training process, the joint self-supervised loss is used to optimize the cross-view features.Abundant experiment studies on numerous benchmarks verify the superiority of EMVCC in comparison to some state-of-the-art clustering methods. The codes are available at https://github.com/YiLiu1999/EMVCC.

Local collaborative representation (CR) has drawn much attention in exploring data relationships due to considering local knowledge in the global linear combination, subsequently, local CR-based graph embedding methods have been applied to dimensionality reduction of hyperspectral image (HSI). However, HSI data with nonlinear distribution cannot be handled with pure linear combination accurately. Furthermore, the existing local knowledge in terms of binary relations between pairwise neighbors makes it hard to learn the accurate local structure among neighborhood sets through local CR-based graph embedding. To this end, this paper proposes a novel multiple neighborhood-aware nonlinear collaborative analysis (MNNCA) method. Relying on the primary and secondary neighborhoods, a dual-level neighborhood reconstruction is designed to search for optimal neighbors and mine the common attributes within the neighborhood. With the reconstruction information, a nonlinear extend multiple neighborhood-aware collaborative representation (NE-MNACR) model is built on nonlinear geodesic constraint and multi-neighborhood-aware items. It can explore the collaborative relationship among multiple neighborhood sets in the nonlinear space of HSI data. By preserving the multivariate local structure instead of pairwise local relations, a pair of collaborative structure preservation graphs are constructed to realize the final embedding of HSI data. Experimental results on serval HSI data sets demonstrate the superior performance of the proposed MNNCA method and NE-MNACR model in comparison with some state-of-the-art DR methods and local CR models.

Hyperspectral anomaly detection (HAD) aims to label each hyperspectral image (HSI) pixel as background or anomaly, in a totally unsupervised manner. Thus, a fine background representation is vital to obtain good HAD performance. This article introduces background endmember representation and proposes a novel HAD method termed learnable background endmember with subspace representation (LEBSR). First, the HSI is unmixed to simultaneously obtain the background endmembers and their abundances. The three constraints of$p$-norm, sum-to-one, and nonnegativity work together to promote a more meaningful and accurate background endmember representation. In addition, a mapping matrix with orthogonality is jointly optimized to transform the priori backgrounds into the background endmember subspace, and then the mapped priori backgrounds are approximated to the low-rank representation (LRR) with the background endmembers. With the methodology, the backgrounds can be well reconstructed under the guidance of the priori background information to accurately detect anomalous pixels with the reconstructed residuals. The experimental results on several HSI datasets verify the superior performance of LEBSR than the state-of-the-art methods.https://github.com/HalongL/HAD-LEBSR

Infrared Small Target Detection (IRSTD) is a challenging task of identifying small targets with low signal-to-noise ratios in complex backgrounds. Traditional methods in the complex background of IRSTD lead to a large number of false alarms and missdetections. Although CNN-based methods have made progress in IRSTD, how to extract more effective information and fully utilize inter-layer information remains an unresolved issue. Therefore, this paper proposed a Dual-Encoder Multi-stage Feature Fusion Network (DMFNet). Specifically, we designed a dual-encoder with different inputs to capture more effective small target feature information. We then designed a Receptive Field Expansion Attention Module (REAM) to incorporate non-local contextual information. In the decoding phase, the Triple Cross-layer Fusion Module (TCFM) was developed to exchange the low-level spatial details and the high-level semantic information for preserving more small target information in deeper layers. Finally, by concatenating multi-scale features from various layers of the decoder, more discriminative feature maps were generated to clearly describe the infrared small targets. Experimental results on the NUDT-SIRST, NUAA-SIRST, and IRSTD-1k datasets demonstrated that DMFNet outperforms some other state-of-the-art methods, achieving superior detection performance. Codes: https://github.com/BJZHOU2000/DMFNet.

Cross-scene classification of hyperspectral image (HSI) based on single-source domain generalization (SDG) focuses on developing a model that can effectively classify images from unseen target domains using only source domain images, without the need for retraining. Most existing SDG approaches for cross-scene classification rely on convolutional neural networks (CNNs). However, the convolutional kernel operation causes the model to emphasize local object features, which can lead to overfitting on the source domain and limits its ability to generalize. Recently, methods based on the state space model (SSM) have demonstrated excellent performance in image classification by capturing global features across different image patches. Building on this inspiration, we propose a novel approach called dynamic token augmentation mamba (DTAM), which aims to explore the potential of SSMs in the cross-scene classification of HSI. The method gradually focuses on the global features of the image by constructing hidden states for HSIs unfolded into long sequences. To further enhance the global features of HSIs, we design a dynamic token augmentation (DTA) module to transform the sample features by perturbing the contextual information while preserving the object information tokens. Additionally, we introduce a loss of classified compensation combined with labels of random samples to suppress the excessive narrowing of the feature range learned by the model. Comprehensive extensive experiments on three publicly available HSI datasets show that the proposed method outperforms the state-of-the-art (SOTA) method. Our code is available athttps://github.com/Varro-pepsi/DTAM.

Transformers has gained widespread adoption in remote sensing image (RSI) segmentation. However, RSI has densely overlapping terrain and significant shadow, making it challenging to segment the blended boundaries of terrains that are the hard classes. Currently, most transformer-based methods construct the self-attention with a sliding window, which influences the feature receptive fields to conquer the intersecting and overlapping objects. Additionally, they often rarely focus specifically on the representation of these hard segmentation objects. To overcome these challenges, we propose a novel Enhancing Semantic Mask Segmentation Network (ESMS-Net) framework including a local-global joint encoder, an auxiliary enhanced encoder, and a multiscale dense decoder. In the local-global joint encoder, we construct a Pyramid Pooling AtrousFormer (PPAFormer) that performs the self-attention with a pyramid-structured atrous sliding window, which enhances the range of receptive fields and the global representation performance. Meanwhile, we construct the dual-feature fusion module (DFFM) and multilevel feature weighted fusion (MFWF) in the multiscale dense decoder to reduce information loss and facilitate the interaction of deep semantic information. For the auxiliary enhanced encoder, we develop a semantic mask based on the predicted results to maintain the hard segmentation classes, and then use the same structure as the first two stages of the local-global joint encoder to learn the hard regions again. Extensive experiments demonstrate the proposed ESMS-Net can achieve significant improvements for segmentation performance compared with the state-of-the-art methods on the ISPRS-Vaihingen and Potsdam datasets. The code will be available athttps://github.com/Wzysaber/ESMS-Net.

Due to the lack of labeled information and the high spectral variability in high-dimensional hyperspectral images (HSI), HSI clustering has emerged as an effective unsupervised approach for HSI information extraction and classification. Deep clustering methods have achieved significant success in unsupervised HSI classification (HSIC) and have gained increasing attention. However, these methods have limitations in terms of robustness, adaptability, and feature representation when dealing with complex large-scale HSI datasets. Therefore, this paper introduced a novel Self-supervised Double-Structure Transformer (SDST) approach for hyperspectral image clustering. Specifically, in our approach, we designed a shared Autoformer structure based on autoencoder to learn the global properties of HSI data by fusing the multi-level features from autoencoder with Transformer. Furthermore, we proposed a siamese Dual-Former Graph Module with superpixel-level features for fewer nodes, which reveals long-dependency graph convolutional features, resulting in more precise graph structure features. By constructing graph with long-dependencies, this module significantly preserves the properties of global dependencies, while focusing on the local features of each superpixel to better represent the fine-grained local details. Finally, we designed a Joint Optimization Module to jointly optimize the double-structure model composed of the shared Autoformer Module and the siamese Dual-Former Graph Module. To validate the effectiveness of the proposed SDST method, we conducted a series of experiments on the Salinas, Botswana, Indian Pines, and Houston2013 datasets. The proposed SDST achieves competitive clustering accuracies compared with the state-of-the-art clustering methods. Codes: https://github.com/YiLiu1999/SDST.

Hyperspectral target detection (HTD) has been a critical issue in the field of Earth observation, with widespread applications in both military and civilian domains. However, existing deep learning-based HTD methods are hindered due to insufficient and low-quality prior training samples, as well as inadequate background suppression capabilities. To address these issues, this article proposes an adversarial sample generation-based multiscale Siamese network (AGMS) for HTD. First, the AGMS utilizes the idea of generative adversarial learning based on the prior few targets and diverse backgrounds to generate adversarial target-background sample pairs, thereby producing high-quality training samples, which enhances the distinctiveness between the target and background samples by adversarially training the generator to produce the target/background samples. In addition, to further highlight the targets and suppress the backgrounds, a difference amplification loss and an adaptive weighted binary cross-entropy loss are proposed. Finally, a multiscale convolutional Siamese network model is designed to explore the generated spectral information at multiple levels and achieve target detection through contrastive learning. Numerous experimental results on four real HSI datasets verify the superiority of the AGMS in comparison to many classical and recently proposed HTD methods. The codes are available athttps://github.com/ShissHAN/AGMS.

Multi-temporal Hyperspectral images (HSIs) have wide applications in change detection (CD) of different land-covers for their rich spectral features and image details. Traditional supervised learning-based HSI CD algorithms often rely on a substantial number of labeled samples. However, it requires a significant cost in sample annotation. In this paper, we propose a diff-feature contrast enhancement network (DCENet) for semi-supervised HSI CD, which leverages a limited number of labeled samples to guide the training process and a large number of unlabeled samples to improve the confidence of change detection. To achieve this, a differential fusion attention (DFA) sub-network is constructed to extract temporal features from the initial input HSI patches. The dual-branch siamese enhancement module (SEM) is utilized to enhance the generalization of differential features in the feature maps. Herein, multi-scale Kullback-Leibler divergence and feature-enhanced probabilistic contrast loss are designed to constrain the SEM. The proposed method excels at detecting subtle changes in bi-temporal HSIs simultaneously improving the generalization performance of networks. The visual and quantitative experimental results on four HSI datasets show that the proposed DCENet outperforms the compared state-of-the-art methods for HSI CD. Codes: https://github.com/Zhoutya/ChangeDetection-DCENet.

Semi-supervised learning (SSL) plays a crucial role in airborne laser scanning (ALS) point cloud semantic segmentation to reduce the cost of sample labeling. However, the prevailing semi-supervised approaches mainly focus on local and global feature aggregation, which neglects the multiscale and neighborhood structure properties of ALS point clouds. To address this issue, we propose an innovative approach called the Hybrid Structured Constraint Network (HSCN) for semi-supervised semantic segmentation of ALS point clouds. HSCN makes full use of a large number of unlabeled samples to guide the model training under limited labeled samples. To process the unlabeled samples, we construct a global awareness loss (GAL) to constrain the global distribution of point clouds. Then, we also design a multiscale geometric structure similarity metric loss (MLS) to align the neighborhood structure for point clouds at different scales. In addition, we utilize the multiscale features to develop a multilevel fused pseudo-label generator for obtaining high-value pseudo-labels, and then a pseudo-label loss (PLS) is constructed to reduce the class mean probability discrepancies. The proposed HSCN fully utilizes the multiscale and neighborhood structure properties of unlabeled samples to achieve a robust model under limited labeled samples. Extensive experimental analysis using three benchmark datasets (i.e., ISPRS, LASDU, and DFC2019) reveals that our proposed method achieves comparable advantages to some existing advanced fully supervised approaches, even only 0.1% labeled samples for model training. The code is available athttps://github.com/SC-shendazt/HSCN.

The multi-source stationary CT, where both the detector and X-ray source are fixed, represents a novel imaging system with high temporal resolution that has garnered significant interest. Limited space within the system restricts the number of X-ray sources, leading to sparse-view CT imaging challenges. Recent diffusion models for reconstructing sparse-view CT have generally focused separately on sinogram or image domains. Sinogram-centric models effectively estimate missing projections but may introduce artifacts, lacking mechanisms to ensure image correctness. Conversely, image-domain models, while capturing detailed image features, often struggle with complex data distribution, leading to inaccuracies in projections. Addressing these issues, the Dual-domain Collaborative Diffusion Sampling (DCDS) model integrates sinogram and image domain diffusion processes for enhanced sparse-view reconstruction. This model combines the strengths of both domains in an optimized mathematical framework. A collaborative diffusion mechanism underpins this model, improving sinogram recovery and image generative capabilities. This mechanism facilitates feedback-driven image generation from the sinogram domain and uses image domain results to complete missing projections. Optimization of the DCDS model is further achieved through the alternative direction iteration method, focusing on data consistency updates. Extensive testing, including numerical simulations, real phantoms, and clinical cardiac datasets, demonstrates the DCDS model's effectiveness. It consistently outperforms various state-of-the-art benchmarks, delivering exceptional reconstruction quality and precise sinogram.

Face verification has seen remarkable progress that benefits from large-scale publicly available databases. However, it remains a challenge how to generalize a pretrained face verification model to a new scenario with a limited amount of data. In many real-world applications, the training database only contains a limited number of identities with two images for each identity due to the privacy concern. In this article, we propose to transfer knowledge from a pretrained unmasked face verification model to a new model for verification between masked and unmasked faces, to meet the application requirements during the COVID-19 pandemic. To overcome the lack of intra-class diversity resulting from only a pair of masked and unmasked faces for each identity ($\text{i.e.},$two shots for each identity), a static prototype classification function is designed to learn features for masked faces by utilizing unmasked face knowledge from the pretrained model. Meanwhile, a contrastive constrained embedding function is designed to preserve unmasked face knowledge of the pretrained model during the transfer learning process. By combining these two functions, our method uses knowledge acquired from the pretrained unmasked face verification model to proceed with verification between masked and unmasked faces with a limited amount of training data. Extensive experiments demonstrate that our method can perform better than state-of-the-art methods for verification between masked and unmasked faces in the few-shot transfer learning setting.

Semantic segmentation of airborne laser scanning (ALS) point clouds using deep learning is a hot research in remote sensing and photogrammetry. A current trend is to aggregate contextual features from different scales for boosting network generalization and diversity discrimination capabilities. One main challenge is how to achieve effective fusion with multiscale information. In this letter, we propose a muti-level context feature fusion network (MCFN) for semantic segmentation of ALS point cloud based on an encoder-decoder structure. More specifically, we design the squeeze-expansion shared MLP module (SE-MLP) following kernel point convolution (KPConv) in the encoding stage, which can extend the receptive field of KPConv. To aggregate low-level features and high-level representations, we establish channel self-attention between skip connections. In the decoding stage, we develop a cross-layer attention fusion module (CAF) to generate additional discriminative channel features by fusing multi-scale features at different upsampling layers. Experiments on the ISPRS and LASDU datasets demonstrate the superiority of the proposed method. Code: https://github.com/SC-shendazt/MCFN.

Partially labeled data learning (PLDL), including partial label learning (PLL) and partial multi-label learning (PML), has been widely used in nowadays data science. Researchers attempt to construct different specific models to deal with the different classification tasks for PLL and PML scenarios respectively. The main challenge in training classifiers for PLL and PML is how to deal with ambiguities caused by the noisy false-positive labels in the candidate label set. The state-of-the-art strategy for both scenarios is to perform disambiguation by identifying the ground-truth label(s) directly from the candidate label set, which can be summarized into two categories: 'the identifying method' and 'the embedding method'. However, both kinds of methods are constructed by hand-designed heuristic modeling under considerations like feature/label correlations with no theoretical interpretation. Instead of adopting heuristic or specific modeling, we propose a novel unifying framework called A Unifying Probabilistic Framework for Partially Labeled Data Learning (UPF-PLDL), which is derived from a clear probabilistic formulation, and brings existing research on PLL and PML under one theoretical interpretation with respect to information theory. Furthermore, the proposed UPF-PLDL also unifies 'the identifying method' and 'the embedding method' into one integrated framework, which naturally incorporates the feature and label correlation considerations. Comprehensive experiments on synthetic and real-world datasets for both PLL and PML scenarios clearly demonstrate the superiorities of the derived framework.

Graph convolutional network (GCN) as a combination of deep learning and graph learning has gained increasing attention in hyperspectral image (HSI) classification. However, most GCN methods consider the simple point-to-point structure between two pixels rather than the high-order structure of multiple pixels, which is contradict with the real feature distribution of ground object. And the nonlinear property of HSI also brings challenge for precise structural representation in GCN. To tackle these problems, this work proposes a structure preserved hypergraph convolution network (SPHGCN). It first builds a multiple neighborhood reconstruction (MNR) model to reveal the essential resemblance of multiple pixels in nonlinear spectral feature space. With the high-order structure, SPHGCN designs the hypergraph convolution operation for irregular feature aggregation among similar pixels from different regions, which achieves more discriminative features from multiple pixel nodes. Meanwhile, a structure preservation layer is built to optimize the distribution of convolutional features under the guidance of high-order structure. Moreover, SPHGCN integrates local regular convolution and irregular hypergraph convolution to learn the structured semantic feature of HSI. This strategy breaks the boundary restriction in traditional convolution and aggregates semantic feature across different image patches. Experiments on three HSI data sets indicate that SPHGCN outperforms a few state-of-the-art methods for HSI classification.

Hyperspectral image (HSI) anomaly detection (AD) generally considers background pixels as low-rank distribution and anomaly pixels as sparse distribution. However, it is usually difficult to construct an accurate background dictionary for the background pixels composed of different land-covers, and completely separate sparse anomaly targets from various complicated background pixels with complex mixed noise interference. To address these challenges, we propose an anti-noise hierarchical mutual-incoherence-induced discriminative learning (AHMID) method for AD of HSI. A structural incoherence constraint is designed to constrain the inherent dissimilarity and incoherence between background and anomalies for improving their separability. Then, a first-order statistic constraint is conducted on targets to enhance the anomaly representation, and a decentralization constraint is used on background to suppress the background representation. Meanwhile, a mixed noise model is constructed by ℓ1,1-norm and Frobenius norm to improve the anti-noise performance. Finally, a hierarchical alternating strategy is developed to gradually optimize the background and anomalies. Experiments on six HSI AD datasets show that the proposed method outperforms a few state-of-the-art AD algorithms. Code: https://github.com/HalongL/HAD-AHMID.

For hyperspectral image (HSI) classification, two branch networks generally use the convolution neural networks (CNNs) to extract the spatial features and the long short-term memory (LSTM) to learn the spectral features. However, CNN with a local kernel neglects the global properties of the whole HSI. LSTM doesn’t consider the macroscopic and detailed information of spectra. In this paper, we propose a dual-view spectral and global spatial feature fusion network (DSGSF) to extract the spatial-spectral features for HSI classification, including a spatial subnetwork and a spectral subnetwork. In the spatial subnetwork, we propose a global spatial feature representation model based on the encoder-decoder structure with channel attention and spatial attention to learn the global spatial features. In the spectral subnetwork, we design a dual-view spectral feature aggregation model with view attention to learn the diversity of spectral features. By fusing the two subnetworks, we construct DSGSF to extract the spatial-spectral features of HSI with strong discriminating performance. Experimental results on three public datasets illustrate that the proposed method can achieve competitive results compared with the state-of-the-art methods. Code: https://github.com/RZWang-WH/DSGSF.

For hyperspectral image (HSI) change detection (CD), multiscale features are usually used to construct the detection models. However, the existing studies only consider the multiscale features containing changed and unchanged components, which is difficult to represent the subtle changes between bitemporal HSIs in each scale. To address this problem, we propose a multiscale diff-changed feature fusion network (MSDFFN) for HSI CD, which improves the ability of feature representation by learning the refined change components between bitemporal HSIs under different scales. In this network, a temporal feature encoder–decoder subnetwork, which combines a reduced inception (RI) module and a cross-layer attention module to highlight the significant features, is designed to extract the temporal features of HSIs. A bidirectional diff-changed feature representation (BDFR) module is proposed to learn the fine changed features of bitemporal HSIs at various scales to enhance the discriminative performance of the subtle change. A multiscale attention fusion (MSAF) module is developed to adaptively fuse the changed features of various scales. The proposed method can not only discover the subtle change in bitemporal HSIs but also improve the discriminating power for HSI CD. Experimental results on three HSI datasets show that MSDFFN outperforms a few state-of-the-art methods.

Kernel point convolution (KPConv) can effectively represent the point features of point cloud data. However, KPConv-based methods just consider the local information of each point, which is very difficult to characterize the intrinsic properties of ALS point clouds for complex laser scanning conditions. Therefore, we rethink KPConv and propose a recurrent residual dual attention network (RRDAN) based on the encoder-decoder structure for the semantic segmentation of ALS point cloud data. In the encoder stage, we design an attention kernel point convolution (AKPConv) block by using a scaling factor of batch normalization to highlight the significant channel information. Then, we use the AKPConv block to develop a recurrent residual kernel attention (RRKA) module to iteratively aggregate the local neighborhood features. In the decoder stage, we design a global and local channel attention (GLCA) module with global connection and local 1D convolution to interact the global and local information after fusing the upsampled high-level representations and the skip-connected low-level features. In addition, to reduce the influence of the long-tail distribution of reflection intensity, we apply gamma transformation to correct the data as normal distribution. The proposed RRDAN can achieve diversified feature aggregation to implement the refined semantic segmentation of ALS point clouds. We evaluate our method on two ALS datasets (i.e., ISPRS and DCF2019) to demonstrate its performance compared to a few advanced methods. Code: https://github.com/SC-shendazt/RRDAN.

Convolutional neural networks (CNNs) for hyperspectral image (HSI) classification have generated good progress. Meanwhile, graph convolutional networks (GCNs) have also attracted considerable attention by using unlabeled data, broadly and explicitly exploiting correlations between adjacent parcels. However, the CNN with a fixed square convolution kernel is not flexible enough to deal with irregular patterns, while the GCN using the superpixel to reduce the number of nodes will lose the pixel-level features, and the features from the two networks are always partial. In this paper, to make good use of the advantages of CNN and GCN, we propose a novel multiple feature fusion model termed attention multi-hop graph and multi-scale convolutional fusion network (AMGCFN), which includes two sub-networks of multi-scale fully CNN and multi-hop GCN to extract the multi-level information of HSI. Specifically, the multi-scale fully CNN aims to comprehensively capture pixel-level features with different kernel sizes, and a multi-head attention fusion module is used to fuse the multi-scale pixel-level features. The multi-hop GCN systematically aggregates the multi-hop contextual information by applying multi-hop graphs on different layers to transform the relationships between nodes, and a multi-head attention fusion module is adopted to combine the multi-hop features. Finally, we design a cross attention fusion module to adaptively fuse the features of two sub-networks. AMGCFN makes full use of multi-scale convolution and multi-hop graph features, which is conducive to the learning of multi-level contextual semantic features. Experimental results on three benchmark HSI datasets show that AMGCFN has better performance than a few state-of-the-art methods.

Graph can achieve good performance to extract the low-dimensional features of hyperspectral image (HSI). However, the present graph-based methods just consider the individual information of each sample in a certain characteristic, which is very difficult to represent the intrinsic properties of HSI for the complex imaging condition. To better represent the low-dimensional features of HSI, we propose a multistructure unified discriminative embedding (MUDE) method, which considers the neighborhood, tangential, and statistical properties of each sample in HSI to achieve the complementarity of different characteristics. In MUDE, we design the intraclass and interclass neighborhood structure graphs with the local reconstruction structure of each sample; meanwhile, we also utilize the adaptive tangential affine combination structure to construct the intraclass and interclass tangential structure graphs. To further enhance the discriminating performance between different classes, we consider the influence of the statistical distribution difference for each sample to develop an interclass Gaussian weighted scatter model. Then, an embedding objective function is constructed to enhance the intraclass compactness and the interclass separability and obtain more discriminative features for HSI classification. Experiments on three real HSI datasets show that the proposed method can make full use of the structure information of each sample in different characteristics to achieve the complementarity of different features and improve the classification performance of HSI compared with the state-of-the-art methods.

RNA-binding proteins (RBPs) play a significant part in several biological processes in the living cell, such as gene regulation and mRNA localization. Several deep learning methods, especially the model based on convolutional neural network(CNN), have been used to predict the binding sites. However, previous methods fail to represent RNA secondary structure features. The traditional deep learning methods generally transform the RNA secondary structure to a regular matrix that cannot reveal the topological structure information of RNA. To effectively extract the structure features of RNA, we propose an RNA secondary structure representation network (RNASSR-Net) based on graph convolutional neural network (GCN) and convolution neural network (CNN) for RBP binding prediction. RNASSR-Net constructs the graph model derived from the RNA secondary structure to learn the topological properties of RNA. Then, it obtains the spatial importance of each base in RNA with CNN to guide the representation of the RNA secondary structure. Finally, RNASSR-Net combines the structure and sequence features to predict the binding sites. Experimental results demonstrate the proposed method outperforms a few state-of-the-art methods on the benchmark datasets and gets a higher improvement on the small-size data. Besides, the proposed RNASSR-Net is also used to detect the accurate motifs compared with the experimentally verified motifs, which reveals the binding region location and RNA structure interpretation for some biological guidance in the future.

Gradient staleness is a major side effect in decoupled learning when training convolutional neural networks asynchronously. Existing methods that ignore this effect might result in reduced generalization and even divergence. In this paper, we propose an accumulated decoupled learning (ADL), which includes a module-wise gradient accumulation in order to mitigate the gradient staleness. Unlike prior arts ignoring the gradient staleness, we quantify the staleness in such a way that its mitigation can be quantitatively visualized. As a new learning scheme, the proposed ADL is theoretically shown to converge to critical points in spite of its asynchronism. Extensive experiments on CIFAR-10 and ImageNet datasets are conducted, demonstrating that ADL gives promising generalization results while the state-of-the-art methods experience reduced generalization and divergence. In addition, our ADL is shown to have the fastest training speed among the compared methods.

Domain adaptation is widely used in the field of remote sensing, which can transfer the existing knowledge to new tasks and promote performance. When applied in the field of scene classification, it can be called cross-scene classification. Previous cross-scene classification methods mainly consider the coarse-grained alignment in the global aspect, which may ignore the structures behind the data and lose the local information with respect to specific categories. To implement fine-grained alignment, we present an adversarial fine-grained adaptation network (AFGAN) which simultaneously captures the complex structures behind the data distributions to improve the discriminability and reduce the local discrepancy of different domains to align the relevant category distributions. Experimental results based on three existing scene classification datasets demonstrate the effectiveness of AFGAN.

Graph learning is an effective technique to reduce the dimensionality of hyperspectral image (HSI) and improve classification result. However, the previous graph methods don't consider the local structure of each pixel in HSI. HSI has a complex non-linear structure, and the local structure can be regarded as a linear distribution. Therefore, we propose a local structure graph discriminant embedding (LSGDE) method to better reveal the intrinsic properties of HSI. This method constructs an intraclass and an interclass structure graphs to compact the intraclass samples and separate the interclass samples. Meanwhile, an interclass weighted scatter based on probability distribution is designed to enhance the discriminative ability of different classes. Then, a projection matrix can be obtained to map high-dimensional data into a low-dimensional space. Experiments on the HoustonU data set show that LSGDE can achieve better performance than the related DR methods.

Representation-based target detectors for hyperspectral imagery (HSI) have recently aroused a lot of interests. However, existing methods ignore the dictionary structure and cannot guarantee an informative and discriminative representation of test pixels for target detection. To alleviate the problem, this letter proposes a novel sparse and dense hybrid representation-based target detector (SDRD). The proposed detector adopts the idea that the relationship between the background and the target sub-dictionaries is a collaborative competition. The structure of the dictionary is discovered and preserved by learning a sparse and dense hybrid representation for test pixel. Benefitting from this, a compact and discriminative representation can be obtained to better represent the test pixel for an improved detection performance. Experimental results on several HSI data sets verify the effectiveness of SDRD in comparison with several state-of-the-art methods.

Hyperspectral image (HSI) contains complex multiple structures. Therefore, the key problem analyzing the intrinsic properties of an HSI is how to represent the structure relationships of the HSI effectively. Hypergraph is very effective to describe the intrinsic relationships of the HSI. In general, Euclidean distance is adopted to construct the hypergraph. However, this method cannot effectively represent the structure properties of high-dimensional data. To address this problem, we propose a sparse-adaptive hypergraph discriminant analysis (SAHDA) method to obtain the embedding features of the HSI in this letter. SAHDA uses the sparse representation to reveal the structure relationships of the HSI adaptively. Then, an adaptive hypergraph is constructed by using the intraclass sparse coefficients. Finally, we develop an adaptive dimensionality reduction mode to calculate the weights of the hyperedges and the projection matrix. SAHDA can adaptively reveal the intrinsic properties of the HSI and enhance the performance of the embedding features. Some experiments on the Washington DC Mall hyperspectral data set demonstrate the effectiveness of the proposed SAHDA method, and SAHDA achieves better classification accuracies than the traditional graph learning methods.

The graph embedding (GE) methods have been widely applied for dimensionality reduction of hyperspectral imagery (HSI). However, a major challenge of GE is how to choose the proper neighbors for graph construction and explore the spatial information of HSI data. In this paper, we proposed an unsupervised dimensionality reduction algorithm called spatial-spectral manifold reconstruction preserving embedding (SSMRPE) for HSI classification. At first, a weighted mean filter (WMF) is employed to preprocess the image, which aims to reduce the influence of background noise. According to the spatial consistency property of HSI, SSMRPE utilizes a new spatial-spectral combined distance (SSCD) to fuse the spatial structure and spectral information for selecting effective spatial-spectral neighbors of HSI pixels. Then, it explores the spatial relationship between each point and its neighbors to adjust the reconstruction weights to improve the efficiency of manifold reconstruction. As a result, the proposed method can extract the discriminant features and subsequently improve the classification performance of HSI. The experimental results on the PaviaU and Salinas hyperspectral data sets indicate that SSMRPE can achieve better classification results in comparison with some state-of-the-art methods.

Dimensionality reduction (DR) is an important way of improving the classification accuracy of a hyperspectral image (HSI). Graph learning, which can effectively reveal the intrinsic relationships of data, has been widely used in the case of HSIs. However, most of them are based on a simple graph to represent the binary relationships of data. An HSI contains complex high-order relationships among different samples. Therefore, in this article, we propose a hybrid-graph learning method to reveal the complex high-order relationships of the HSI, termed enhanced hybrid-graph discriminant learning (EHGDL). In EHGDL, an intraclass hypergraph and an interclass hypergraph are constructed to analyze the complex multiple relationships of a HSI. Then, a supervised locality graph is applied to reveal the binary relationships of a HSI which can form the complementarity of a hypergraph. Simultaneously, we also construct a weighted neighborhood margin model to boost the difference of samples from different classes. Finally, we design a DR model based on the intraclass hypergraph, the interclass hypergraph, the supervised locality graph, and the weighted neighborhood margin to improve the compactness of the intraclass samples and the separability of the interclass samples, and an optimal projection matrix can be achieved to extract the low-dimensional embedding features of the HSI. To demonstrate the effectiveness of the proposed method, experiments have been conducted on the Indian Pines, PaviaU, and HoustonU data sets. The experimental results show that EHGDL can generate better classification performance compared with some related DR methods. As a result, EHGDL can better reveal the complex intrinsic relationships of a HSI by the complementarity of different characteristics and enhance the discriminant performance of land-cover types.

Nonlocal similar patches are effectively used in the Gaussian prior denoising model. However, it is difficult to learn an accurate Gaussian model for hyperspectral image (HSI) with noisy and limited similar patches, which will result in unstable Gaussian parameters (mean and covariance). In this letter, several techniques are proposed to overcome the noisy and small sample problems for HSI denoising. For Gaussian parameters, we propose the adaptive weighted mean of nonlocal similar patches and use a positive semidefinite constraint on the covariance parameter. In addition, an iterative manner is used to achieve more accurate parameters. The proposed method can achieve more robust Gaussian model for HSI denoising. Experiments on a HSI demonstrate the effectiveness of the proposed algorithm compared with the traditional methods for HSI denoising.

Hyperspectral image (HSI) contains a large number of spatial-spectral information, which will make the traditional classification methods face an enormous challenge to discriminate the types of land-cover. Feature learning is very effective to improve the classification performances. However, the current feature learning approaches are mostly based on a simple intrinsic structure. To represent the complex intrinsic spatial-spectral of HSI, a novel feature learning algorithm, termed spatial-spectral hypergraph discriminant analysis (SSHGDA), has been proposed on the basis of spatial-spectral information, discriminant information, and hypergraph learning. SSHGDA constructs a reconstruction between-class scatter matrix, a weighted within-class scatter matrix, an intraclass spatial-spectral hypergraph, and an interclass spatial-spectral hypergraph to represent the intrinsic properties of HSI. Then, in low-dimensional space, a feature learning model is designed to compact the intraclass information and separate the interclass information. With this model, an optimal projection matrix can be obtained to extract the spatial-spectral features of HSI. SSHGDA can effectively reveal the complex spatial-spectral structures of HSI and enhance the discriminating power of features for land-cover classification. Experimental results on the Indian Pines and PaviaU HSI data sets show that SSHGDA can achieve better classification accuracies in comparison with some state-of-the-art methods.

Hyperspectral image (HSI) contains a large number of spatial-spectral information, which will make the traditional classification methods face an enormous challenge to discriminate the types of land-cover. Feature learning is very effective to improve the classification performances. However, the current feature learning approaches are most based on a simple intrinsic structure. To represent the complex intrinsic spatial-spectral of HSI, a novel feature learning algorithm, termed discriminant spatial-spectral hypergraph learning (DSSHL), has been proposed on the basis of spatial-spectral information and hypergraph learning. DSSHL constructs an intraclass spatial-spectral hypergraph and an interclass spatial-spectral hypergraph to represent the intrinsic properties of HSI. Then, a feature learning model is designed to compact the intraclass information and separate the interclass information. DSSHL can effectively reveal the complex spatial-spectral structures of HSI for land-cover classification. Experimental results on the Salinas HSI data set shows that DSSHL can achieve better classification accuracies in comparison with some state-of-the-art methods.

Marginal Fisher analysis (MFA) exploits the margin criterion to compact the intraclass data and separate the interclass data, and it is very useful to analyze the high-dimensional data. However, MFA just considers the structure relationship of neighbor points, and it cannot effectively represent the intrinsic structure of hyperspectral image (HSI) that possesses many homogenous areas. In this paper, we proposed a new dimensionality reduce (DR) model, termed local geometric structure Fisher analysis (LGSFA), for HSI classification. At first, this method computes the reconstruction point of each point with its intraclass neighbor points. Then, an intrinsic graph and a penalty graph are constructed to reveal the intraclass and interclass relationship, respectively. Finally, the neighbor points and corresponding reconstruction points are used to enhance the intraclass compactness and interclass separability in low-dimensional space. LGSFA can effectively reveal the intrinsic manifold structure and obtains the discriminating feature of HSI data. Experiments on Salinas HSI data set show that the proposed LGSFA algorithm performs the best classification results than other state-of-the-art methods.

To utilize the spatial information and manifold structure in hyperspectral image (HSI), we propose a spatial-spectral manifold reconstruction classifier (SSMRC) for HSI classification in this paper. The SSMRC method firstly uses a mean filter to combine the spatial neighborhood information. Then the manifold reconstruction error utilizes as a measurement of how well a data point resides on a manifold, and the class label can be assigned with the minimum reconstruction error. It makes full use of spatial information and discriminating manifold structure in HSI, and the classification ability is further improved. The effectiveness of the proposed method is verified on real HSI data set with promising results.

The graph embedding (GE) framework is very useful to extract the discriminative features of hyperspectral images (HSIs) for classification. However, a major challenge of GE is how to select a proper neighborhood size for graph construction. To overcome this drawback, a new semisupervised discriminative learning algorithm, which is called the semisupervised sparse manifold discriminative analysis (S3MDA) method, was proposed by using manifold-based sparse representation (MSR) and GE. The proposed algorithm utilizes MSR to obtain the sparse coefficients of labeled and unlabeled samples. Then, it constructs a within-class graph and a between-class graph using the sparse coefficients of labeled samples, as well as an unsupervised graph with the sparse coefficients of unlabeled samples. Finally, it uses these graphs to obtain a projection matrix for feature extraction (FE) of HSI in a low-dimensional space. The S3MDA method not only inherits the merits of MSR to reveal the sparse manifold properties of data but also enhances interclass separability and intraclass compactness to improve the discriminating power for classification. Extensive experiments on two real HSI data sets obtained with a reflective optics system imaging spectrometer and an airborne visible/infrared imaging spectrometer show that the proposed algorithm is significantly superior to other state-of-the-art FE methods in terms of classification accuracy.

Locally linear embedding (LLE) depends on the Euclidean distance (ED) to select the k-nearest neighbors. However, the ED may not reflect the actual geometry structure of data, which may lead to the selection of ineffective neighbors. The aim of our work is to make full use of the local spectral angle (LSA) to find proper neighbors for dimensionality reduction (DR) and classification of hyperspectral remote sensing data. At first, we propose an improved LLE method, called local spectral angle LLE (LSA-LLE), for DR. It uses the ED of data to obtain large-scale neighbors, then utilizes the spectral angle to get the exact neighbors in the large-scale neighbors. Furthermore, a local spectral angle-based nearest neighbor classifier (LSANN) has been proposed for classification. Experiments on two hyperspectral image data sets demonstrate the effectiveness of the presented methods.