Article
Geography, Physical
Yuli Sun, Lin Lei, Xiang Tan, Dongdong Guan, Junzheng Wu, Gangyao Kuang
Summary: This research proposes an unsupervised image regression method based on the inherent structure consistency between heterogeneous images for change detection in multimodal remote sensing images. The proposed method effectively addresses the problem of comparing heterogeneous images and achieves improved detection accuracy compared to state-of-the-art algorithms.
ISPRS JOURNAL OF PHOTOGRAMMETRY AND REMOTE SENSING
(2022)
Article
Geochemistry & Geophysics
Hongruixuan Chen, Naoto Yokoya, Chen Wu, Bo Du
Summary: In this paper, an unsupervised multimodal change detection method is proposed. It measures the similarity of two structural relationships by learning the graph representations and generates difference images. Finally, an adaptive fusion strategy and a postprocessing approach are employed to refine the detection results.
IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING
(2022)
Article
Geochemistry & Geophysics
Yuli Sun, Lin Lei, Li Liu, Gangyao Kuang
Summary: Multimodal change detection (MCD) is a challenging topic in remote sensing due to the unavailability of directly comparing multimodal images. This article proposes a structural regression fusion (SRF)-based method to reduce the influence of structural asymmetry and improve image transformation performance in MCD. SRF incorporates fusion into the regression process and yields three types of constraints to perform the fused image transformation. The proposed SRF is verified on six real datasets and outperforms some state-of-the-art methods.
IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING
(2023)
Article
Environmental Sciences
Kuowei Xiao, Yuli Sun, Lin Lei
Summary: This study proposes a change detection framework based on change alignment, utilizing complementary information from forward and backward difference maps to enhance domain transformation effects and improve heterogeneous CD performance.
Article
Geography, Physical
Hongruixuan Chen, Naoto Yokoya, Marco Chini
Summary: This paper proposes a Fourier domain structural relationship analysis framework for unsupervised multimodal change detection (FD-MCD), which utilizes modality-independent local and nonlocal structural relationships to tackle the comparison problem of multimodal images. The framework calculates a local frequency consistency metric in the Fourier domain, constructs nonlocal structural relationship graphs for pre-change and post-change images, and models high-order vertex information using graph spectral convolution. An adaptive fusion method based on frequency-decoupling is designed to effectively fuse the local and nonlocal structural difference maps.
ISPRS JOURNAL OF PHOTOGRAMMETRY AND REMOTE SENSING
(2023)
Article
Computer Science, Interdisciplinary Applications
Jing Ke, Yiqing Shen, Yizhou Lu, Yi Guo, Dinggang Shen
Summary: In this paper, an Interaction Information Clustering (IIC) method is proposed to extract locally homogeneous features in mutually exclusive clusters. Trained in an unsupervised paradigm, the framework learns invariant information from multiple spatially adjacent regions for improved classification. Additionally, an adaptive Conditional Random Field (CRF) model is incorporated to detect spatially adjacent image patches of high morphological homogeneity in an offset-constraint free manner.
COMPUTER METHODS AND PROGRAMS IN BIOMEDICINE
(2023)
Article
Environmental Sciences
Shuying Li, Shaowei Wang, Qiang Li
Summary: Active learning is a method that reduces the dependence on labeled samples. However, current active learning methods often fail to distinguish between samples with similar posterior probabilities. To address this issue, a novel algorithm called Joint Posterior Probabilistic Active Learning combined with Conditional Random Field (JPPAL_CRF) is proposed. This algorithm improves the variability between samples by jointly considering all information in the posterior probability matrix, and utilizes a conditional random field approach to optimize classification results by incorporating regional spatial information of hyperspectral images. Experimental results on two common hyperspectral datasets demonstrate the effectiveness of JPPAL_CRF.
Article
Chemistry, Multidisciplinary
Weiwei Hu, Liang He, Hanhan Ma, Kai Wang, Jingfeng Xiao
Summary: Recently, the lexicon method has been proven effective for named entity recognition (NER). However, most existing lexicon-based methods cannot fully utilize common-sense knowledge in the knowledge graph. Therefore, incorporating knowledge into NER has become a challenging and popular research topic. In this study, we propose a knowledge graph-inspired NER method that incorporates common sense using a masking and encoding approach, leading to improved performance.
APPLIED SCIENCES-BASEL
(2022)
Article
Computer Science, Artificial Intelligence
Dazhi Xu, Ming Li, Yan Wu, Peng Zhang, Xinyue Xin, Zhifei Yang
Summary: Propose an unsupervised PolSAR image change detection method based on multiscale graph convolutional network (GCN), which can effectively suppress speckle noise and preserve edge information, improving feature discriminability.
Article
Geochemistry & Geophysics
Pan Shao, Yunqi Yi, Zhewei Liu, Ting Dong, Dong Ren
Summary: This letter presents a novel multiscale decision fusion method for unsupervised change detection based on Dempster-Shafer theory and modified conditional random field. The proposed method effectively combines the multiscale information in images and the spatial contextual information, improving the change detection performance.
IEEE GEOSCIENCE AND REMOTE SENSING LETTERS
(2022)
Article
Computer Science, Artificial Intelligence
Luigi Tommaso Luppino, Mads Adrian Hansen, Michael Kampffmeyer, Filippo Maria Bianchi, Gabriele Moser, Robert Jenssen, Stian Normann Anfinsen
Summary: Image translation with convolutional autoencoders is used for multimodal change detection in bitemporal satellite images. The proposed approach aligns code spaces by capturing relational pixel information and reduces the impact of change pixels on the learning objective. Experimental results demonstrate the effectiveness of this method.
IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS
(2022)
Article
Computer Science, Artificial Intelligence
Jianjin Xu, Zhaoxiang Zhang, Xiaolin Hu
Summary: Recently, the use of unsupervised learning, especially Generative Adversarial Networks (GANs), has gained attention for representation learning. This work focuses on further understanding and utilizing the features learned by GANs. The researchers propose a clustering algorithm, KLiSH, which leverages the linear separability of GANs' features. With KLiSH, they are able to extract fine-grained semantics from GANs trained on different datasets and use the synthesized datasets for various downstream applications such as unsupervised semantic segmentation and semantic-conditional image synthesis.
IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE
(2023)
Article
Computer Science, Artificial Intelligence
Xin Wang, Lixin Han, Jingxian Li, Hong Yan
Summary: The tripartite graph model in recommender systems can better handle data sparsity and cold start issues, improving recommendation metrics such as diversity, recall, and precision. Using the Conditional Random Field algorithm, potentially similar users can be identified, uncovering their preferences, and the random walk method further explores users with similar preferences beyond social relationships.
EXPERT SYSTEMS WITH APPLICATIONS
(2024)
Article
Computer Science, Information Systems
Piotr Bielak, Tomasz Kajdanowicz, Nitesh Chawla
Summary: Representation learning has proposed a novel unsupervised method called AttrE2Vec to learn low-dimensional vector representations for edges in attributed networks. The experimental results demonstrate that the proposed method builds more powerful edge vector representations compared to contemporary approaches, reflected by higher quality measures in downstream tasks.
INFORMATION SCIENCES
(2022)
Article
Computer Science, Artificial Intelligence
Runzhong Wang, Junchi Yan, Xiaokang Yang
Summary: This study proposes an unsupervised framework for graph matching, which can match two or multiple graphs and handle graphs with a mixture of modes. The framework is trained by minimizing the discrepancy between a second-order classic solver and a first-order differentiable Sinkhorn net. Experimental results show that our method performs well in real-world applications such as natural image matching.
IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE
(2023)
Article
Computer Science, Artificial Intelligence
Yuli Sun, Lin Lei, Xiao Li, Hao Sun, Gangyao Kuang
Summary: This paper proposes a new change detection method based on similarity measurement between heterogeneous images, which constructs a graph for each patch to establish a connection between heterogeneous data and measures the change level by comparing graph structures, achieving robust change detection results without leakage of heterogeneous data.
PATTERN RECOGNITION
(2021)
Article
Geochemistry & Geophysics
Ming Li, Lin Lei, Yuli Sun, Xiao Li, Gangyao Kuang
Summary: In this letter, a novel scene classification framework called CL-NL-Net is proposed to improve global scene understanding ability by capturing long-range correlations between different layers. Experimental results show that the method is competitive in terms of classification accuracy.
IEEE GEOSCIENCE AND REMOTE SENSING LETTERS
(2022)
Article
Geochemistry & Geophysics
Lin Lei, Yuli Sun, Gangyao Kuang
Summary: This study proposes an unsupervised change detection method based on adaptive local structure consistency for heterogeneous remote sensing images. Experimental results demonstrate the effectiveness of the proposed method.
IEEE GEOSCIENCE AND REMOTE SENSING LETTERS
(2022)
Article
Geochemistry & Geophysics
Yuli Sun, Lin Lei, Dongdong Guan, Ming Li, Gangyao Kuang
Summary: The study proposes an unsupervised image regression-based change detection method using structure consistency, which adaptively constructs a similarity graph and a superpixel-based Markovian segmentation model to detect changes effectively.
IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING
(2022)
Article
Geochemistry & Geophysics
Xiao Li, Lin Lei, Yuli Sun, Gangyao Kuang
Summary: This article proposes a novel dynamic-hierarchical attention distillation network (DH-ADNet) with multimodal synergetic instance selection (MSIS) for land cover classification using missing data modalities. The method utilizes multimodal data and attention mechanism to achieve better classification performance.
IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING
(2022)
Article
Geochemistry & Geophysics
Yuli Sun, Lin Lei, Xiao Li, Xiang Tan, Gangyao Kuang
Summary: This article proposes a structure consistency-based method for change detection in remote sensing images. By comparing the structures of two images instead of pixel values, the method demonstrates strong robustness and applicability to various scenarios. Additionally, the method shows effectiveness in both homogeneous and heterogeneous change detection, as well as in the seldom-studied case of heterogeneous change detection with multichannel synthetic aperture radar (SAR) images. Through analysis and improvements on the nonlocal patch-based graph (NLPG), the method is made more accurate and robust.
IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING
(2022)
Article
Geography, Physical
Yuli Sun, Lin Lei, Xiang Tan, Dongdong Guan, Junzheng Wu, Gangyao Kuang
Summary: This research proposes an unsupervised image regression method based on the inherent structure consistency between heterogeneous images for change detection in multimodal remote sensing images. The proposed method effectively addresses the problem of comparing heterogeneous images and achieves improved detection accuracy compared to state-of-the-art algorithms.
ISPRS JOURNAL OF PHOTOGRAMMETRY AND REMOTE SENSING
(2022)
Article
Environmental Sciences
Lingjun Zhao, Yuli Sun, Lin Lei, Siqian Zhang
Summary: This paper proposes an auto-weighted structured graph (AWSG)-based regression method for heterogeneous change detection using remote sensing images. The method learns the image structure and performs structure regression to detect changes. Experimental results and comparisons demonstrate the effectiveness of the proposed approach.
Article
Computer Science, Information Systems
Xiang Tan, Li Zhou, Haijun Wang, Yuli Sun, Haitao Zhao, Boon-Chong Seet, Jibo Wei, Victor C. M. Leung
Summary: This article investigates the distributed dynamic spectrum access problem for multiusers in a cognitive radio network. By utilizing deep recurrent Q-networks and cooperative multi-agent reinforcement learning, a distributed offline training and online execution framework is proposed to maximize network throughput. Experimental results show that the algorithm outperforms the state-of-the-art in terms of successful access rate and collision rate.
IEEE INTERNET OF THINGS JOURNAL
(2022)
Article
Environmental Sciences
Kuowei Xiao, Yuli Sun, Lin Lei
Summary: This study proposes a change detection framework based on change alignment, utilizing complementary information from forward and backward difference maps to enhance domain transformation effects and improve heterogeneous CD performance.
Article
Geochemistry & Geophysics
Yuli Sun, Lin Lei, Li Liu, Gangyao Kuang
Summary: Multimodal change detection (MCD) is a challenging topic in remote sensing due to the unavailability of directly comparing multimodal images. This article proposes a structural regression fusion (SRF)-based method to reduce the influence of structural asymmetry and improve image transformation performance in MCD. SRF incorporates fusion into the regression process and yields three types of constraints to perform the fused image transformation. The proposed SRF is verified on six real datasets and outperforms some state-of-the-art methods.
IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING
(2023)
Article
Geochemistry & Geophysics
Kuowei Xiao, Yuli Sun, Gangyao Kuang, Lin Lei
Summary: This paper proposes a new method called CAGSL for heterogeneous change detection, which uses graph structure learning and change alignment constraint to improve the detection accuracy, and its effectiveness is demonstrated through experiments.
IEEE GEOSCIENCE AND REMOTE SENSING LETTERS
(2023)
Article
Geochemistry & Geophysics
Yuli Sun, Lin Lei, Dongdong Guan, Gangyao Kuang, Li Liu
Summary: This article presents a new strategy for solving the heterogeneous change detection (HCD) problem using graph signal processing (GSP). The authors analyze the HCD problem from both the vertex domain and the spectral domain, proposing filtering methods and spectral analysis models for detecting changes between heterogeneous images. The effectiveness of these methods is demonstrated through experiments on real datasets.
IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING
(2022)
Article
Computer Science, Artificial Intelligence
Yuli Sun, Lin Lei, Dongdong Guan, Junzheng Wu, Gangyao Kuang, Li Liu
Summary: This study proposes an image regression method based on structure cycle consistency for change detection in heterogeneous images. The method captures the structure information of the image by constructing a similarity relationship-based graph and performs structure-based regression using an adaptive-weighted distance metric. Experimental results demonstrate the excellent performance of the proposed method.
IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS
(2022)
Article
Computer Science, Artificial Intelligence
Guang-Hai Liu, Zuo-Yong Li, Jing-Yu Yang, David Zhang
Summary: This article introduces a novel image retrieval method that improves retrieval performance by using sublimated deep features. The method incorporates orientation-selective features and color perceptual features, effectively mimicking these mechanisms to provide a more discriminating representation.
PATTERN RECOGNITION
(2024)
Article
Computer Science, Artificial Intelligence
Fengguang Peng, Zihan Ding, Ziming Chen, Gang Wang, Tianrui Hui, Si Liu, Hang Shi
Summary: RGB-Thermal (RGB-T) semantic segmentation is an emerging task that aims to improve the robustness of segmentation methods under extreme imaging conditions by using thermal infrared modality. The challenges of foreground-background distinguishment and complementary information mining are addressed by proposing a cross modulation process with two collaborative components. Experimental results show that the proposed method achieves state-of-the-art performances on current RGB-T segmentation benchmarks.
PATTERN RECOGNITION
(2024)
Article
Computer Science, Artificial Intelligence
Baihong Han, Xiaoyan Jiang, Zhijun Fang, Hamido Fujita, Yongbin Gao
Summary: This paper proposes a novel automatic prompt generation method called F-SCP, which focuses on generating accurate prompts for low-accuracy classes and similar classes. Experimental results show that our approach outperforms state-of-the-art methods on six multi-domain datasets.
PATTERN RECOGNITION
(2024)
Article
Computer Science, Artificial Intelligence
Huikai Liu, Ao Zhang, Wenqian Zhu, Bin Fu, Bingjian Ding, Shengwu Xiong
Summary: Adverse weather conditions present challenges for computer vision tasks, and image de-weathering is an important component of image restoration. This paper proposes a multi-patch skip-forward structure and a Residual Deformable Convolutional module to improve feature extraction and pixel-wise reconstruction.
PATTERN RECOGNITION
(2024)
Article
Computer Science, Artificial Intelligence
Oliver M. Crook, Mihai Cucuringu, Tim Hurst, Carola-Bibiane Schonlieb, Matthew Thorpe, Konstantinos C. Zygalakis
Summary: The transportation LP distance (TLP) is a generalization of the Wasserstein WP distance that can be applied directly to color or multi-channelled images, as well as multivariate time-series. TLP interprets signals as functions, while WP interprets signals as measures. Although both distances are powerful tools in modeling data with spatial or temporal perturbations, their computational cost can be prohibitively high for moderate pattern recognition tasks. The linear Wasserstein distance offers a method for projecting signals into a Euclidean space, and in this study, we propose linear versions of the TLP distance (LTLP) that show significant improvement over the linear WP distance in signal processing tasks while being several orders of magnitude faster to compute than the TLP distance.
PATTERN RECOGNITION
(2024)
Article
Computer Science, Artificial Intelligence
Haitao Tian, Shiru Qu, Pierre Payeur
Summary: This paper proposes a method of target-dependent classifier, which optimizes the joint hypothesis of domain adaptation into a target-dependent hypothesis that better fits with the target domain clusters through an unsupervised fine-tuning strategy and the concept of meta-learning. Experimental results demonstrate that this method outperforms existing techniques in synthetic-to-real adaptation and cross-city adaptation benchmarks.
PATTERN RECOGNITION
(2024)
Article
Computer Science, Artificial Intelligence
Qingsen Yan, Axi Niu, Chaoqun Wang, Wei Dong, Marcin Wozniak, Yanning Zhang
Summary: Deep learning-based methods have achieved remarkable results in the field of super-resolution. However, the limitation of paired training image sets has led researchers to explore self-supervised learning. However, the assumption of inaccurate downscaling kernel functions often leads to degraded results. To address this issue, this paper introduces KGSR, a kernel-guided network that trains both upscaling and downscaling networks to generate high-quality high-resolution images even without knowing the actual downscaling process.
PATTERN RECOGNITION
(2024)
Article
Computer Science, Artificial Intelligence
Yifan Chen, Xuelong Li
Summary: Gait recognition is a popular technology for identification due to its ability to capture gait features over long distances without cooperation. However, current methods face challenges as they use a single network to extract both temporal and spatial features. To solve this problem, we propose a two-branch network that focuses on spatial and temporal feature extraction separately. By combining these features, we can effectively learn the spatio-temporal information of gait sequences.
PATTERN RECOGNITION
(2024)
Article
Computer Science, Artificial Intelligence
Wei Shi, Wentao Zhang, Wei-shi Zheng, Ruixuan Wang
Summary: This article proposes a simple yet effective visualization framework called PAMI, which does not require detailed model structure and parameters to obtain visualization results. It can be applied to various prediction tasks with different model backbones and input formats.
PATTERN RECOGNITION
(2024)
Article
Computer Science, Artificial Intelligence
Xiaobo Hu, Jianbo Su, Jun Zhang
Summary: This paper reviews the latest technologies in pattern recognition, highlighting their instabilities and failures in practical applications. From a control perspective, the significance of disturbance rejection in pattern recognition is discussed, and the existing problems are summarized. Finally, potential solutions related to the application of compensation on features are discussed to emphasize future research directions.
PATTERN RECOGNITION
(2024)
Article
Computer Science, Artificial Intelligence
Andres Felipe Posada-Moreno, Nikita Surya, Sebastian Trimpe
Summary: Convolutional neural networks are widely used in critical systems, and explainable artificial intelligence has proposed methods for generating high-level explanations. However, these methods lack the ability to determine the location of concepts. To address this, we propose a novel method for automatic concept extraction and localization based on pixel-wise aggregations, and validate it using synthetic datasets.
PATTERN RECOGNITION
(2024)
Article
Computer Science, Artificial Intelligence
Peng Bao, Jianian Li, Rong Yan, Zhongyi Liu
Summary: In this paper, a novel Dynamic Graph Contrastive Learning framework, DyGCL, is proposed to capture the temporal consistency in dynamic graphs and achieve good performance in node representation learning.
PATTERN RECOGNITION
(2024)
Article
Computer Science, Artificial Intelligence
Kristian Schultz, Saptarshi Bej, Waldemar Hahn, Markus Wolfien, Prashant Srivastava, Olaf Wolkenhauer
Summary: Research indicates that deep generative models perform poorly compared to linear interpolation-based methods for synthetic data generation on small, imbalanced tabular datasets. To address this, a new approach called ConvGeN, combining convex space learning with deep generative models, has been proposed. ConvGeN improves imbalanced classification on small datasets while remaining competitive with existing linear interpolation methods.
PATTERN RECOGNITION
(2024)
Article
Computer Science, Artificial Intelligence
Khondaker Tasrif Noor, Antonio Robles-Kelly
Summary: In this paper, the authors propose H-CapsNet, a capsule network designed for hierarchical image classification. The network effectively captures hierarchical relationships using dedicated capsules for each class hierarchy. A modified hinge loss is utilized to enforce consistency among the involved hierarchies. Additionally, a strategy for dynamically adjusting training parameters is presented to achieve better balance between the class hierarchies. Experimental results demonstrate that H-CapsNet outperforms competing hierarchical classification networks.
PATTERN RECOGNITION
(2024)
Article
Computer Science, Artificial Intelligence
Lei Liu, Guorun Li, Yuefeng Du, Xiaoyu Li, Xiuheng Wu, Zhi Qiao, Tianyi Wang
Summary: This study proposes a new agricultural image segmentation model called CS-Net, which uses Simple-Attention Block and Simpleformer to improve accuracy and inference speed, and addresses the issue of performance collapse of Transformers in agricultural image processing.
PATTERN RECOGNITION
(2024)
