Article
Environmental Sciences
Shengliang Pu, Yuanfeng Wu, Xu Sun, Xiaotong Sun
Summary: This study proposes a novel method for hyperspectral image classification, which utilizes localized graph convolutional filtering to analyze diversified land covers. Experimental results demonstrate that the presented method offers promising classification performance compared with other popular competitors.
Article
Environmental Sciences
Haron C. Tinega, Enqing Chen, Long Ma, Divinah O. Nyasaka, Richard M. Mariita
Summary: This study proposes a deep 3D/2D genome graph-based network called HybridGBN-SR which is computationally efficient and not prone to overfitting even with extremely few training sample data. It achieves better classification accuracy in hyperspectral image classification by extracting discriminative spectral-spatial features using the three-dimensional (3D) and two-dimensional (2D) Genoblocks trained with very few samples.
Article
Geochemistry & Geophysics
Wentao Yu, Sheng Wan, Guangyu Li, Jian Yang, Chen Gong
Summary: In this article, a GCN model with contrastive learning, called ConGCN, is proposed for HSI classification. It enhances the feature representation ability by exploring supervision signals from both spectral information and spatial relations. The proposed method achieves promising results in both qualitative and quantitative aspects, as demonstrated by extensive experiments on benchmark datasets.
IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING
(2023)
Article
Geochemistry & Geophysics
Bing Yang, Hailiang Ye, Ming Li, Feilong Cao, Shirui Pan
Summary: This article proposes a Global-to-Local decoupling Graph network (GoLoG) for hyperspectral image (HSI) classification. It optimizes both the graph structure and network parameters to capture long-range spatial correlations in HSI while preserving individualized spectral characteristics of each pixel. The proposed GoLoG outperforms other state-of-the-art HSI classification methods.
IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING
(2023)
Article
Environmental Sciences
Hong-Xia Dou, Xiao-Miao Pan, Chao Wang, Hao-Zhen Shen, Liang-Jian Deng
Summary: In this paper, a 3D-based neural network called SSCANet is proposed for denoising remote sensing hyperspectral images. The network consists of a so-called SSCA block, which includes a spatial attention block and a spectral-channel attention block. Experimental results show that the proposed method outperforms other methods in terms of restoration quality.
Article
Geochemistry & Geophysics
Mohammad Joshaghani, Amirabbas Davari, Faezeh Nejati Hatamian, Andreas Maier, Christian Riess
Summary: Hyperspectral remote sensing (HSRS) images with high dimensionality pose challenges for deep neural networks due to limited labeled data. In this study, Bayesian convolutional neural networks (BCNNs) are introduced as an alternative to CNNs, benefiting from Bayesian learning and providing an uncertainty measure. Experimental results on multiple datasets demonstrate that BCNN outperforms non-Bayesian CNNs, random forests, and Bayesian neural networks. BCNN also exhibits better resistance to overfitting and larger capacity for model compression, making it suitable for hardware-constrained settings. The uncertainty measure of BCNN effectively identifies misclassified samples, providing useful information for detecting mislabeled data or rejecting low-confidence predictions.
IEEE GEOSCIENCE AND REMOTE SENSING LETTERS
(2023)
Article
Environmental Sciences
Minghua Zhang, Hongling Luo, Wei Song, Haibin Mei, Cheng Su
Summary: This study introduces a new method called spectral-spatial offset graph convolutional networks (SSOGCN) for hyperspectral image (HSI) classification. In contrast to traditional methods, this approach constructs adjacency matrix using only local pixels to capture richer local spatial context information and reduce computational cost. Experimental results show that SSOGCN outperforms the recent state-of-the-art methods in terms of classification performance.
Article
Engineering, Electrical & Electronic
Bo Feng, Yi Liu, Hao Chi, Xinzhuang Chen
Summary: In this study, a method using residual generative adversarial networks for hyperspectral image classification is proposed, which improves the information exchange between shallow and deep networks by adding a residual structure to the network, extracts deep features of hyperspectral images, and improves classification accuracy. Extensive experiments have shown that the method outperforms comparative methods by 0.7% to 22.3% on OA accuracy on several benchmark hyperspectral datasets.
Article
Computer Science, Information Systems
Monika Sharma, Mantosh Biswas
Summary: This paper describes a unique semisupervised classification technique using a deep learning based hybrid framework (DL-HF) for hyperspectral images. The proposed method improves classification accuracy by pre-labeling unlabeled samples, expanding the training set, and utilizing self-arrangement based on deep learning. Evaluation results demonstrate that the proposed DL-HF algorithm outperforms other competing classification schemes on benchmark datasets.
MULTIMEDIA TOOLS AND APPLICATIONS
(2023)
Article
Geochemistry & Geophysics
Xiaolong Liao, Bing Tu, Jun Li, Antonio Plaza
Summary: In this article, a class-wise graph-embedding-based active learning (CGE-AL) framework is proposed for hyperspectral image classification. The framework utilizes a class-wise graph convolutional network (CGCN) to select informative and uncertain samples for labeling, leading to improved performance compared to other state-of-the-art active learning approaches.
IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING
(2023)
Article
Environmental Sciences
Jiangbo Xi, Okan K. Ersoy, Ming Cong, Chaoying Zhao, Wei Qu, Tianjun Wu
Summary: This paper proposes a wide and deep Fourier network for efficient feature learning in hyperspectral remote sensing image (HSI) classification. The method utilizes pruned features extracted in the frequency domain to extract hierarchical features layer-by-layer. Experimental results show that the proposed method achieves excellent performance in HSI classification, with the ability to be implemented in lightweight embedded computing platforms.
Article
Remote Sensing
Huimin Zhao, Chenchen Wang, Huayue Chen, Tao Chen, Wu Deng
Summary: This paper proposes a hybrid classification method based on dual-channel convolutional neural network (DC-CNN) and kernel extreme learning machine (KELM), called PLDC-KELM, to improve spatial-spectral feature extraction ability and classification accuracy of hyperspectral remote sensing images (HRSI).
INTERNATIONAL JOURNAL OF REMOTE SENSING
(2023)
Article
Computer Science, Artificial Intelligence
Feng Zhao, Junjie Zhang, Zhe Meng, Hanqiang Liu, Zhenhui Chang, Jiulun Fan
Summary: This article proposes a hybrid network called MVAHN for hyperspectral image (HSI) classification, which combines convolutional neural network (CNN) and transformer structures. It also utilizes a graph convolutional module (GCM) to extract multiple types of feature information. Experimental results show that MVAHN achieves high accuracy on various datasets.
EXPERT SYSTEMS WITH APPLICATIONS
(2023)
Article
Computer Science, Artificial Intelligence
Yaoming Cai, Zijia Zhang, Qin Yan, Dongfang Zhang, Mst Jainab Banu
Summary: The proposed Dense Connected Convolutional ELM (DC2ELM) is a simple yet effective deep ELM method for spectral-spatial classification of hyperspectral images. By introducing dense connections and stacked ELM auto-encoders, it can make full use of intermediate feature maps and achieve a deeper architecture, with fewer trainable parameters compared to traditional convolutional neural networks.
Article
Engineering, Electrical & Electronic
Yao Ding, Xiaofeng Zhao, Zhili Zhang, Wei Cai, Nengjun Yang
Summary: In this article, a multiscale graph sample and aggregate network with a context-aware learning method is proposed for HSI classification. This network can learn global and contextual information of the graph effectively, and solve the impact of original input graph errors on classification. Experimental results show the superiority of the proposed method over state-of-the-art methods.
IEEE JOURNAL OF SELECTED TOPICS IN APPLIED EARTH OBSERVATIONS AND REMOTE SENSING
(2021)
Article
Computer Science, Artificial Intelligence
Hao Peng, Ruitong Zhang, Shaoning Li, Yuwei Cao, Shirui Pan, Philip S. Yu
Summary: This paper presents a novel reinforced, incremental, and cross-lingual social event detection architecture, FinEvent, which models social messages into heterogeneous graphs and uses reinforcement learning algorithm to select optimal aggregation thresholds. It addresses the challenges of ambiguous event features, dispersive text contents, and multiple languages in existing event detection methods for streaming social messages, thereby improving accuracy and generalization ability.
IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE
(2023)
Article
Computer Science, Information Systems
Xiang Ying, Zechen Meng, Mankun Zhao, Mei Yu, Shirui Pan, Xuewei Li
Summary: This paper proposes an enhanced representation method that addresses the issue of wrong labeling in distant supervised relation extraction. By incorporating enhanced representations into a gated graph convolutional network, the proposed method achieves significant improvement on two popular datasets.
WORLD WIDE WEB-INTERNET AND WEB INFORMATION SYSTEMS
(2023)
Article
Computer Science, Theory & Methods
Huan Yee Koh, Jiaxin Ju, Ming Liu, Shirui Pan
Summary: Automatic text summarization systems for long documents have become significant in aiding readers' comprehension. This survey provides a comprehensive overview and systematic evaluation of research on long document summarization, including benchmark datasets, summarization models, and evaluation metrics.
ACM COMPUTING SURVEYS
(2023)
Article
Computer Science, Artificial Intelligence
Xiaoyong Mei, Yougen Zhou, Chenjing Zhu, Mengting Wu, Ming Li, Shirui Pan
Summary: Aspect-based sentiment analysis (ABSA) aims to predict sentiment polarity for given aspects in sentences using interactions between aspect terms and their contexts. This paper proposes a disentangled linguistic graph model (DLGM) to enhance transparency and performance in sentiment polarity classification.
KNOWLEDGE-BASED SYSTEMS
(2023)
Article
Computer Science, Artificial Intelligence
Ghazaleh Niknam, Soheila Molaei, Hadi Zare, David Clifton, Shirui Pan
Summary: Graph representation learning is an effective tool for graph analysis with machine learning. This paper proposes a method that improves the performance of the VGAE model using Gaussian Mixture Model and adversarial regularization, and demonstrates remarkable performance on clustering and link prediction tasks.
Article
Computer Science, Artificial Intelligence
Xin Zheng, Yanbo Fan, Baoyuan Wu, Yong Zhang, Jue Wang, Shirui Pan
Summary: This study investigates the impact of sticker-based physical attacks on face recognition and proposes a novel robust physical attack framework to simulate adversarial stickers under different physical-world conditions. The Curriculum Adversarial Attack algorithm gradually adapts to environmental variations and improves the attack performance. A standardized testing protocol is constructed for fair evaluation.
PATTERN RECOGNITION
(2023)
Article
Computer Science, Artificial Intelligence
Soheila Molaei, Nima Ghanbari Bousejin, Hadi Zare, Mahdi Jalili, Shirui Pan
Summary: This paper introduces a novel representation learning approach based on spectral convolutions for improving classification tasks on graph data by aggregating local information.
IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS
(2023)
Editorial Material
Physics, Multidisciplinary
Xinyi Wang, Yuexia Zhang, Xuzhen Zhu, Fei Xiong, Wei Wang, Shirui Pan
FRONTIERS IN PHYSICS
(2023)
Article
Biology
Fuyi Li, Xudong Guo, Yue Bi, Runchang Jia, Miranda E. Pitt, Shirui Pan, Shuqin Li, Robin B. Gasser, Lachlan JM. Coin, Jiangning Song
Summary: A deep learning-based approach called Digerati was developed for the rapid and accurate identification of PE and PPE family proteins. Digerati achieved a significantly better performance (-18-20%) than alignment-based methods. It is expected to facilitate high-throughput identification and analysis of PE/PPE family members.
COMPUTERS IN BIOLOGY AND MEDICINE
(2023)
Article
Computer Science, Artificial Intelligence
Chaojie Li, Wensen Jiang, Yin Yang, Shirui Pan, Gang Huang, Lijie Guo
Summary: This article introduces the solution deployed at Alibaba in preparing for its annual "Double 11" promotion event. This solution predicts the sales volume of new items by considering their connections with older products with long sales history. Experimental results demonstrate consistent performance gains compared to existing methods for sales forecast.
IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS
(2023)
Article
Computer Science, Artificial Intelligence
Sheng Wan, Yibing Zhan, Shuo Chen, Shirui Pan, Jian Yang, Dacheng Tao, Chen Gong
Summary: Contrastive learning is a key technique for self-supervised representation learning, but the uniform negative sampling strategy limits the expressive power of contrastive models. To address this, the article proposes an adaptive sampling strategy called AdaS and introduces an auxiliary polarization regularizer to improve the performance of graph contrastive learning.
IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS
(2023)
Article
Computer Science, Artificial Intelligence
Zonghan Wu, Shirui Pan, Guodong Long, Jing Jiang, Chengqi Zhang
Summary: AutoGCN is proposed to capture the full spectrum of graph signals and automatically update the bandwidth of graph convolutional filters, overcoming the limitations of existing graph convolutional networks that only work as low-pass filters.
IEEE TRANSACTIONS ON KNOWLEDGE AND DATA ENGINEERING
(2023)
Article
Computer Science, Artificial Intelligence
Di Jin, Zhizhi Yu, Pengfei Jiao, Shirui Pan, Dongxiao He, Jia Wu, Philip S. Yu, Weixiong Zhang
Summary: Community detection is a fundamental task in network analysis, aiming to partition a network into sub-structures to reveal their latent functions. Traditional approaches utilize probabilistic graphical models, while new approaches use deep learning to convert networked data into low dimensional representation. There is a lack of understanding of the theoretical and methodological underpinnings of community detection, which is critical for the future development of network analysis.
IEEE TRANSACTIONS ON KNOWLEDGE AND DATA ENGINEERING
(2023)
Article
Computer Science, Artificial Intelligence
Yu Zheng, Huan Yee Koh, Ming Jin, Lianhua Chi, Khoa T. Phan, Shirui Pan, Yi-Ping Phoebe Chen, Wei Xiang
Summary: Multivariate time-series anomaly detection is crucial in various applications, but existing methods have limitations in capturing nonlinear relations and explicit pairwise correlations. To address these issues, we propose a novel method called CST-GL, which explicitly captures pairwise correlations and utilizes a graph neural network to encode spatial information and capture long-range dependence over time.
IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS
(2023)
Article
Geochemistry & Geophysics
Bing Yang, Hailiang Ye, Ming Li, Feilong Cao, Shirui Pan
Summary: This article proposes a Global-to-Local decoupling Graph network (GoLoG) for hyperspectral image (HSI) classification. It optimizes both the graph structure and network parameters to capture long-range spatial correlations in HSI while preserving individualized spectral characteristics of each pixel. The proposed GoLoG outperforms other state-of-the-art HSI classification methods.
IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING
(2023)
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)