At present, spectral clustering is an important branch of unsupervised learning, and its application in deep learning has been widely concerned. However, for high-dimensional sparse datasets, the complexity of network scale leads to parameter explosion, and static Gaussian kernel often has wrong preset data structure. To overcome these challenges, we propose a novel deep clustering model, Deep Clustering Based on Sparse Kolmogorov-Arnold Network (KAN) and Spectral Constraint. It contains a deep sparse clustering framework, in which sparse KAN and the orthogonal layer are designed to enhance the sparsity of the activation function matrix, reduce the number of parameters and improve the stability of model convergence. Additionally, we add an adaptive optimized affinity matrix based on spectral constraint, which overcomes the limitations of static Gaussian kernels, and improves the performance and stability of spectral constraint. Experimental results on both synthetic and real datasets demonstrate that our model outperforms existing methods in clustering performance, computational efficiency, and stability.

Vehicle object detection is a fundamental component of intelligent transportation systems, yet its deployment in resource-constrained environments is limited by the trade-off between accuracy and computational efficiency. This work systematically examines the relationship between network depth and detection performance through controlled experiments on both convolutional and attention-based architectures. The results reveal that accuracy does not scale indefinitely with depth, but instead exhibits diminishing returns and converges to a task-dependent performance plateau. A mutual information-based analysis attributes this saturation to fundamental limitations in information retention and representational efficiency. Motivated by this insight, we propose the TritonFocus Network (TF-Net), an architecture that integrates large-Kernel contextual perception with small-Kernel local aggregation for efficient feature representation. Extensive evaluations on the UA-DETRAC and BITVehicle benchmarks demonstrate that TF-Net achieves a state-of-the-art accuracy–efficiency trade-off among lightweight detectors. TF-Net achieves a relative detection accuracy improvement of approximately 5.8%, while maintaining high computational efficiency and approaching twice the inference speed of the baseline model. These findings validate the efficacy of saturation-aware architectural optimization and provide theoretical and practical guidance for deploying high-performance detection models in edge computing scenarios.

Cross-view geo-localization (CVGL) offers a promising alternative for positioning in GNSS-constrained environments through visual matching techniques. Extreme viewpoint variations and the complexity of real-world scenes present significant challenges to this task. However, current methods primarily focus on learning single-scale features, which may be inadequate for practical applications. Although some approaches attempt to incorporate multi-scale representations, they may suffer from unimodal bias arising from structural discrepancies among model branches, limiting effective multi-scale feature extraction. To address these issues, we propose a fully multi-branch network architecture, named BEMN, which is designed to learn multi-scale robust feature representations. Specifically, we construct a multi-branch backbone network based on pretrained visual models and design a two-stage training strategy. In the first stage, a separate training scheme is employed to thoroughly optimize each branch of the network, and a joint feature alignment (JFA) module is introduced to align cross-view features. The entire network is fine-tuned in the second stage, where a frequency domain adjustment (FDA) module is designed to improve performance. To further assess the generalization ability of CVGL methods, we establish Xian-37, a highly challenging CVGL test dataset featuring complex real scenes captured from diverse platforms and viewpoints. Experimental results across multiple public benchmarks validate the superiority of our approach, achieving state-of-the-art performance and demonstrating outstanding generalization capabilities. Our code and model are available at https://github.com/VERYBC/BEMN.

Obtaining the earth-fixed coordinates is a fundamental requirement for long-distance unmanned aerial vehicle (UAV) flight. Global navigation satellite systems are the most common location model, but their signals are susceptible to interference from obstacles and complex electromagnetic environments. To solve this issue, a visual localization framework based on multi-source image feature learning (VL-MFL) is proposed. In the proposed framework, the UAV is located by mapping airborne images to the satellite images with absolute coordinate positions. Firstly, for the heterogeneity issues caused by the different imaging environments of drone and satellite images, a lightweight Siamese network based on 3-D attention mechanism is proposed to extract the consistent features from the multi-source images. Secondly, to overcome the problem of inaccurate localization caused by the large receptive field of traditional convolutional neural networks, the cell-divided strategy is imported to strengthen the position mapping relationship of multi-source images features. Finally, based on similarity measurement, a confidence evaluation mechanism is established and a search region prediction method is proposed, which is effectively improved the accuracy and efficiency in matching localization. To evaluate the location performance of the proposed framework, several related methods are compared and analysed in details. The results on the real-world datasets indicate that the proposed method has achieved outstanding location accuracy and real-time performance.

The core challenge of multi-view scene matching is to effectively extract features from multi-view images, which is a key factor to achieve robust scene matching. This paper delves into methodologies for enhancing the multi-view robustness of scene matching, with the following key contributions: 1) This paper propose the metric feature consistency principle which emphasize the necessity of implementing accurate correspondence between drone and satellite images. To verify the principle, consistent feature enhancement for channel, spatial, and hybrid dimensions is explored. As a counterexample, the shuffle operation is used to break the consistency of dimension semantic information. Experiments show that the mAP is reduced by about 20% after breaking the consistency relationship of metric features. 2) Built upon the principle, this paper introduces a scene matching framework named DUMM (Dimensionally Unified Metric Model). Utilizing the multi-dimensional feature enhancement model, it effectively enhances the correspondence of the dual-branch features within the siamese network. 3) This paper is the first to introduce the feature dimension, frequency domain feature. By the upper and lower bounds of the cosine transform function, the negative effects of cross-view variations can be effectively mitigated, thus enhancing the overall robustness. The introduction of frequency features improves the mAP by 2.54% compared with the method of improving the dimensional consistency ofH×W×C, verifying the positive impact of the fusion of frequency domain features on enhancing the robustness of scene matching. Nevertheless, it remains imperative to adhere to the principle of feature dimension consistency across all additional frequency dimensions.

VHR remote sensing images have abundant ground features and details, but it is a great challenge for machine understanding. The "same object with different spectral" problem caused by environment changes, such as seasonal alternation, bad weather and shadow, is the biggest challenge in multitemporal image change detection, which is more prominent in VHR images. For this problem, a novel difference guided VHR image change detection (DGCD) method is proposed in this paper. In the feature learning stage of DGCD model, difference features are used to guide the feature extraction to suit with the change detection task. In order to make the model focus on the change features, both of the spatial and channel attention mechanism are introduced. Finally, for the edge region of VHR image which is hard to be discriminated, a new edge enhanced loss function based on BCL loss is designed. Experiments on public datasets show the superiority of proposed DGCD method. It has good generalization ability in different classical challenging scenarios. Compared with the representative methods in recent years, the proposed DGCD method performs better on VHR image change detection.

Scene matching involves establishing a mapping relationship between heterogeneous images, which is crucial for drone visual geo-localization. However, it poses a significant challenge for multi-view images such as those captured by drones and satellites. To address this issue, this paper proposes an end-to-end geo-localization framework named F3-Net for calculating the similarity of multi-source and multi-view images. The key contributions of F3-Net are as follows: 1) The Split and Fusion (SF) module is designed to fully exploit the features through the global self-attention mechanism. 2) To improve the multi-view semantic features, a Target Feature Enhancement (TFE) module is introduced, based on the principle of invariance target semantic consistency. 3) After multi-view feature learning, a Feature Alignment and Unity (FAU) module with Earth Mover distance is used to calculate the similarity of non-aligned features. F3-Net fully exploits the multi-source image feature correspondence and multi-view image semantic consistency. Different from the traditional siamese network, the features of multi-view images are regarded as probability distribution, so F3-Net can quantify and eliminate the feature differences of multi-view images in the learning process. Experiments show that F3-Net can effectively overcome multi-view changes and achieve high accuracy on University-1652 dataset.

Visual localization is an important but challenging task for unmanned aerial vehicles (UAV). Matching real-time UAV orthophotos to pre-existing georeferenced satellite images is the key problem for this task. However, UAV and satellite images are inconsistent in image styles, perspectives, and times. In this paper, a new fully convolutional siamese network is proposed to extract similar features for multi-source images. The Squeeze-and-Excitation structure is integrated into the densely connected network to adapt to multi-scale features and the texture differences of different regions. Besides, a loss function with a progressive sampling strategy is utilized to mine the similarity of matching multi-source images and improve the description compactness among dimensions. Extensive experimental results with in-depth analysis are provided, which indicate that the proposed framework can significantly improve the matching performance of the learned descriptor.

Unmanned aerial vehicles (UAVs) are widely applied in various fields, which is located by the global position system (GPS) in most cases. However, in the GPS-denied cases, visual localization becomes very important. In complicated environments, such as weak illumination and ground objects changed, visual localization is unstable. This letter presents a UAV visual localization model with a block joint learning network (BJN). Different from the traditional feature extraction-comparison paradigm, the proposed BJN extracts the joint features of the input images at the same time, so as to fully mine the coupling relationship between the multi-source images. Besides this, to overcome the challenges of inconsistency style changes in image matching, the saliency feature based on the attention mechanism and the traditional edge feature operator are introduced in joint feature learning. To evaluate the performance of the proposed model, the experiments on the simulated dataset and the real dataset are given. Both the results on simulated and real datasets indicate that the proposed model is effective on multi-source image matching and UAV visual localization.

Hyperspectral image (HSI) often suffers from various noise disturbances which makes the interpretation difficult. To solve this problem, a lot of HSI denoising algorithms have been proposed and widely used. Although many convolution neural network (CNN) based denoising methods have achieved successful performance in independently and identically distributed (i.i.d) Gaussian denoising, they are still limited to remove inconsistent noise, and even worse than traditional representative algorithms like total variation regularized low-rank matrix factorization (LRTV) and low-rank matrix recovery (LRMR). In this letter, a new multiscale residual learning network (MSRHSID) is proposed for HSIs denoising. In this network, a noise estimation network is used in our proposed method to obtain the image noise prior to achieve the reduction of inconsistent noise. At the same time, an efficient multiscale residual module (MRM) is employed to further improve the denoising effect. Both of the denoising experiments on synthetic and real-data HSIs show that this proposed MSRHSID outperforms the state-of-the-art methods.

The nonnegative matrix factorization (NMF)-combined spatial–spectral information has been widely applied in the unmixing of hyperspectral images (HSIs). However, how to select the appropriate similarity pixels and explore the spatial information and how to adapt the unmixing algorithm to complex data are both great challenges. In this article, we propose a novel unmixing method named spatial–spectral neighborhood preserving NMF (SSNPNMF) for incomplete and noisy HSI data. First, a spatial–spectral kernel regularizer is introduced to preprocess the HSI, which can reduce noise and complete missing elements. Second, a distance metric SSD based on spatial–spectral information is designed to select similar pixels in the image. Subsequently, the spatial–spectral relationship of the selected first$k$similar pixels is used to reconstruct the image and obtain the reconstruction matrix. Finally, the reconstruction matrix is used to constrain the abundances and improve the unmixing performance. Experimental results on synthetic data and Cuprite data indicate that SSNPNMF has a more effective unmixing performance compared with the state-of-the-art methods.

Due to the inconsistent imaging environment, the styles of multitemporal multispectral images (MSIs) are quite different, such as image brightness and transparency. For multitemporal MSIs with different styles, the “same object with different spectra” problem is one of the biggest challenges in change detection. To overcome the challenge, a novel unsupervised spatial–spectral feature learning (FL) framework based on style transformation (ST) (called STFL-CD) is proposed for MSI change detection in this article. For dual-temporal MSIs, the proposed STFl-CD algorithm consists of two phases: ST and spatial–spectral FL. Since the image styles are inconsistent under different imaging environments, the first innovation is to transform the image styles through unmixing and reconstruction. Through ST, the challenge of the “same object with different spectra” problem will be reduced fundamentally. By introducing the attention mechanism, the other innovation is to extract the joint spectral–spatial change features based on a 3-D convolutional neural network with spatial and channel attention. In addition, for multitemporal MSIs, a multitemporal version STFL-CD (MT-STFL-CD) framework is designed based on a recurrent neural network to learn the correlation features between multitemporal remote sensing images. Both of the visual and quantitative results on the real MSI datasets indicate that the proposed unsupervised STFL-CD frameworks have significant advantages on multitemporal MSI change detection. In particular, the performance of the proposed unsupervised STFL-CD algorithm is even comparable to that of the state-of-the-art supervised or semisupervised methods.

Because of the inevitable noise interference in hyperspectral images (HSIs), the understanding and application of HSIs are seriously restricted. To solve this problem, the research on the data-driven neural network-based denoising method has become a hotspot in recent years. However, for HSIs with inconsistent and mixed noises, the traditional data-driven denoising algorithms have obvious limitations on generalization ability. In order to overcome these drawbacks, a novel partial densenet (Partial-DNet) model with noise intensity estimation is proposed for HSIs blind denoising in this article. In the proposed Partial-DNet model, the noise intensity of each band is estimated in the first and then fused with the observed images to generate the feature maps by introducing the channel attention mechanism. Finally, a novel multiscale neural network is explored to extract the spatial–spectral joint features. The contributions of this article can be summarized as follows: 1) the noise intensity of each band is estimated as a prior to guide the blind denoising framework suit with different data sets adaptively; 2) a Partial-DNet model is proposed to extract multiscale spatial–spectral features more efficient to maintain the details better while denoising; and 3) the experiments on both simulated and real HSI data sets indicate that the proposed denoising framework can be used to remove the inconsistent mixed noises in HSIs adaptively. Compared with the other state-of-the-art denoising methods, HSIs denoised by the proposed Partial-DNet algorithm not only have a higher PSNR index but also have higher classification accuracy under the same situation.

Because of the complexity of imaging environment, hyper-spectral remote sensing images (HSIs) often suffer from different kinds of noise. Despite the success in natural image denoising, most of the existing CNN-based HSIs denoising methods still suffer from the problem of inadequate noise suppression and insufficient feature extraction. In this paper, a novel HSIs denoising algorithm based on an enhanced non-local cascading network with attention mechanism (ENCAM) is proposed, which can extract the joint spatial-spectral feature more effectively. The main contributions include: (1) the non-local structure is introduced to enlarge the receptive field to extract the spatial features more effectively; (2) multi-scale convolutions and channel attention module are applied to enhance extracted multi-scale features; (3) a cascading residual dense structure is used to extract different frequency features. Both of the theoretical analysis and the experiments indicate that the proposed method is superior to the other state-of-the-art methods on HSIs denoising.

Change detection (CD) for multispectral remote sensing images is an important approach to observe the changes of the earth. However, the same object usually has different spectra in multi-temporal images, which is one of the biggest challenges for CD. To overcome this problem, a novel unsupervised CD approach based on spectral transformation and joint spectral-spatial feature learning (STCD) is proposed for multispectral images in this paper. By exploring the relationship between imaging environment and the object spectra, the spectral transformation is used to suppress the phenomenon of “same object with different spectra”. Besides, a detection network with joint spectral-spatial feature learning is designed to extract the spectral-spatial features simultaneously to make the CD algorithm more robust. Both theoretical analyses and experiment results proved that the proposed STCD method is superior to the state-of-the-art unsupervised methods on multispectral images CD.

This paper presents a new framework with a siamese feature aggregation network (SFANet) for visual localization based on remote sensing scene matching. Specifically, the presented framework predicts the location of a query image by finding the matching remote sensing images with geographical information. We employ the fully convolutional networks (FCNs) and a siamese network of NetVLAD to aggregate local features and learn the global representations for images from different sources. A new soft margin loss function is established for the network. Geographic coordinates of the query images are obtained by calculating the similarity with satellite images. We also collect a multi-scale dataset that contains 136959 images from 45653 locations. Various experiments are carried out on it. Experimental results show the effectivity of the proposed method.

With the help of satellite geographical information, we present an innovative framework for localizing precisely while handling the varying views and different sources. We construct a convolutional neural network named Attentive Siamese-like Net (ASN) which can extract the multi-view scene representation. On top of it, a database retrieval system is established to search the realistic geographic coordinates quickly and reliably. For handling a complicated scene, a mass of visual data is collected from google satellite image and Google Earth Software. Experiments are carried out on two datasets of different scales and geographical range, which shows the superiority and effectiveness of our method.

This paper presents a concept of noise similarity (NS), which can be used to refine the comparison of noisy patch and enhance the denoising power of the nonlocal means (NLM) filter. The fact behind this concept is that the similarity of noisy patch should depend on not only the underlying signal (noise free patches), but also the noise. Based on the concept of noise similarity, we derived a double NS (DNS) model, which converts the denoising problem into the problem of reducing two kinds of noise: one is the superimposed additive noise; the other is the deviation error, defined as another kind of noise denoting the difference between similar pixels on their true intensities. The former corresponds to noise suppression, while the latter corresponds to the restoration of image details. To evaluate the effectiveness of the DNS model, we proposed an iterative version of the NLM filter, where the two noise similarities can work collaboratively in the framework of maximum a posterior. Finally, the experimental results demonstrate that the proposed approach can provide competitive performance when compared with other state-of-the-art NLM filters.

This letter proposed a new nonlocal polarimetric synthetic aperture radar (PolSAR) filter based on discriminative similarity measure (DSM). The DSM, which is implemented in the form of maximum a posteriori (MAP), deals with the speckle and the underlying speckle-free signal of PolSAR data individually. Due to its MAP form, the DSM achieves good balance between the similarity of the speckle and the similarity of the underlying speckle-free signal. And then this balance can lead to excellent performance on both speckle smoothing and detail preservation. Results are shown to demonstrate its competence when compared with the state-of-the-art methods.

In this letter, a simple and effective unsupervised approach based on the combined difference image and$k$-means clustering is proposed for the synthetic aperture radar (SAR) image change detection task. First, we use one of the most popular denoising methods, the probabilistic-patch-based algorithm, for speckle noise reduction of the two multitemporal SAR images, and the subtraction operator and the log ratio operator are applied to generate two kinds of simple change maps. Then, the mean filter and the median filter are used to the two change maps, respectively, where the mean filter focuses on making the change map smooth and the local area consistent, and the median filter is used to preserve the edge information. Second, a simple combination framework which uses the maps obtained by the mean filter and the median filter is proposed to generate a better change map. Finally, the$k$-means clustering algorithm with$k = 2$is used to cluster it into two classes, changed area and unchanged area. Local consistency and edge information of the difference image are considered in this method. Experimental results obtained on four real SAR image data sets confirm the effectiveness of the proposed approach.

This paper presents a nonlocal Lee (NL-Lee) filter for polarimetric synthetic aperture radar despeckling. In the proposed NL-Lee filter, a kind of hybrid patch similarity measure is constructed by combining together the structure similarity introduced by the nonlocal means (NLM) filter and the homogeneity similarity introduced by the Lee filter, which works in a distributive way. This combination leads to two important advantages for the proposed nonlocal filter. One is the improved robustness to the NLM parameters such as patch size and search neighborhood size, since the patch regularity assumption can be enhanced by the introduced hybrid patch similarity; the other one is the better performance tradeoff between speckle removal and detail preservation, because of the good balance between structure similarity and homogeneity similarity obtained by the framework of the proposed NL-Lee filter. Experimental results are given to demonstrate its competitive denoising performance.