Article
Environmental Sciences
Zhongwei Li, Shunxiao Shi, Leiquan Wang, Mingming Xu, Luyao Li
Summary: In this paper, an unsupervised generative adversarial network method is proposed to address the issues of background generation capability and redundant information disturbance in hyperspectral anomaly detection. By enhancing background spatial features and employing irredundant pooling, the proposed method achieves better performance compared to other algorithms.
Article
Geochemistry & Geophysics
Kazi Tanzeem Shahid, Ioannis D. Schizas
Summary: This study introduces a novel unsupervised neural network-based scheme for unmixing hyperspectral pixels, incorporating autoencoder structure, kernelization layer, cross-product layer, K-means clustering, and radial basis functions. The proposed method is highly versatile and outperforms recent state-of-the-art unmixing methods in extensive testing across semisynthetic and real-world datasets.
IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING
(2022)
Article
Geochemistry & Geophysics
Jiaping Zhong, Weiying Xie, Yunsong Li, Jie Lei, Qian Du
Summary: This article presents a novel approach using generative adversarial networks (GANs) for separating background and anomaly in hyperspectral anomaly detection. By explicitly constraining the background spectral samples to enhance background reconstruction while weakening anomaly reconstruction, superior background-anomaly separability is achieved.
IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING
(2021)
Article
Biochemical Research Methods
Xuesong Wang, Zhihang Hu, Tingyang Yu, Yixuan Wang, Ruijie Wang, Yumeng Wei, Juan Shu, Jianzhu Ma, Yu Li
Summary: We propose a novel framework for aligning and integrating single-cell RNA-seq and single-cell ATAC-seq data, aiming to promote single-cell multi-omics research.
Article
Computer Science, Information Systems
Tianzi Zhao, Liang Jin, Xiaofeng Zhou, Shuai Li, Shurui Liu, Jiang Zhu
Summary: This research proposes an unsupervised anomaly detection approach based on adversarial memory autoencoders for multivariate time series to solve the problem of precisely determining anomalies in the data. The method uses an encoder to encode the input data into low-dimensional space to acquire a feature vector and utilizes a memory module to learn the prototype patterns and update the feature vectors. Two decoders are then used to reconstruct the input data, and the Peak Over Threshold (POT) method is used to calculate the threshold for anomaly detection.
CMC-COMPUTERS MATERIALS & CONTINUA
(2023)
Article
Geochemistry & Geophysics
Chunhui Zhao, Chuang Li, Shou Feng, Wei Li
Summary: This study introduces a novel spectral-spatial hyperspectral anomaly detection method, SSCRSAE, which combines deep feature extraction and AD tasks while utilizing spatial information. Experimental results show its performance surpasses eight other state-of-the-art anomaly detectors.
IEEE GEOSCIENCE AND REMOTE SENSING LETTERS
(2022)
Article
Computer Science, Artificial Intelligence
Weiying Xie, Jie Lei, Shuo Fang, Yunsong Li, Xiuping Jia, Mingsuo Li
Summary: The study introduces an unsupervised method, dual feature extraction network (DFEN), for hyperspectral anomaly detection, which gradually establishes discrimination between original data and background, calculates spatial and spectral anomaly scores, and reduces false alarm rate for comprehensive detection results.
PATTERN RECOGNITION
(2021)
Article
Computer Science, Artificial Intelligence
Tao Jiang, Weiying Xie, Yunsong Li, Jie Lei, Qian Du
Summary: This article proposes a weakly supervised discriminative learning approach using spectral constrained generative adversarial networks for hyperspectral anomaly detection. The network enhances discrimination between anomaly and background, and includes an end-to-end architecture with a novel spectral constraint. Experimental results demonstrate the unique promise of this approach.
IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS
(2022)
Article
Computer Science, Artificial Intelligence
Jie Lei, Meiqi Li, Weiying Xie, Yunsong Li, Xiuping Jia
Summary: A novel unsupervised hyperspectral change detection (UHCD) framework is proposed in this paper, designed for hyperspectral images with high dimensions and low availability. The framework possesses distinctive properties including unsupervised spectral mapping, enhanced feature quality, and spatial attribute optimization.
Article
Environmental Sciences
Wuxia Zhang, Huibo Guo, Shuo Liu, Siyuan Wu
Summary: This paper proposes a Hyperspectral Anomaly Detection method based on Attention-aware Spectral Difference Representation (HAD-ASDR) to reconstruct more accurate background models for improved detection. The method consists of three modules: ASDRM, CAE-BRM, and JSIA-ADM. Experimental results show that the proposed method achieves better or comparable results on five data sets.
Article
Radiology, Nuclear Medicine & Medical Imaging
Haibo Zhang, Wenping Guo, Shiqing Zhang, Hongsheng Lu, Xiaoming Zhao
Summary: This paper proposes an unsupervised learning method for deep anomaly detection based on an improved adversarial autoencoder. By using a module called chain of convolutional block (CCB), the proposed method provides considerable advantages in capturing the distribution of normal samples in image space and latent vector space.
JOURNAL OF DIGITAL IMAGING
(2022)
Article
Computer Science, Artificial Intelligence
Mohammadreza Salehi, Atrin Arya, Barbod Pajoum, Mohammad Otoofi, Amirreza Shaeiri, Mohammad Hossein Rohban, Hamid R. Rabiee
Summary: A novel training algorithm for autoencoders is proposed in this paper to address the novelty detection problem by enhancing adversarial robustness to facilitate learning more semantically meaningful features. Experimental results show that the proposed method outperforms or is competitive with the state-of-the-art on various benchmark datasets.
Article
Environmental Sciences
Jingyan Zhang, Xiangrong Zhang, Licheng Jiao
Summary: This paper proposes a dual-view hyperspectral anomaly detection method that considers anomaly analysis at both pixel and subpixel levels. The spectral angular distance is used at the pixel level to calculate similarities for spatial consistency analysis, while the difference between anomaly and background at the subpixel level is analyzed through unmixing. The detection results from both levels are fused to obtain the anomalies.
Article
Geochemistry & Geophysics
Sertac Arisoy, Nasser M. Nasrabadi, Koray Kayabol
Summary: The proposed method is a completely unsupervised pixel-wise anomaly detection approach for hyperspectral images, consisting of data preparation, reconstruction, and detection steps. Three different deep autoencoding adversarial network (AEAN) models are used for generating synthesized HSIs, and a weighted RX (WRX) -based detector is utilized for anomaly detection, outperforming other detectors in benchmark experiments.
IEEE GEOSCIENCE AND REMOTE SENSING LETTERS
(2022)
Article
Engineering, Electrical & Electronic
Xiaoyi Wang, Liguo Wang, Qunming Wang, Anna Vizziello, Paolo Gamba
Summary: This study proposes a method based on three-dimensional convolution and global spatial-spectral attention network to address the issue of spectral variation in hyperspectral images. A new background suppression strategy is also proposed. Experimental results show that the proposed method achieves higher accuracy in target detection.
IEEE JOURNAL OF SELECTED TOPICS IN APPLIED EARTH OBSERVATIONS AND REMOTE SENSING
(2023)
Article
Geochemistry & Geophysics
Xin Zhang, Weiying Xie, Yunsong Li, Jie Lei, Qian Du, Geng Yang
Summary: This article proposes a band selection method called rank-aware generative adversarial network (R-GAN) to address the issues of band interaction and information saliency evaluation in traditional clustering-based methods. The proposed R-GAN combines interpretability and interband relevance through centralized reference feature extraction with GAN, and refines the reference feature with a saliency estimation strategy. Experimental results demonstrate that R-GAN can effectively address spectral saliency and select more informative band subsets, outperforming other competitors in detection and classification tasks.
IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING
(2022)
Article
Geochemistry & Geophysics
Yunsong Li, Tao Jiang, Weiying Xie, Jie Lei, Qian Du
Summary: This study introduces a sparse coding-inspired generative adversarial network for weakly supervised anomaly detection from hyperspectral images. By integrating a background-category searching step and an SC-inspired regularized network, a robust and interpretable model is developed, which detects anomalies in a latent space.
IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING
(2022)
Article
Engineering, Electrical & Electronic
Gang He, Li Xu, Jie Lei, Weiying Xie, Yunsong Li, Yibo Fan, Jinjia Zhou
Summary: This paper introduces a deep neural network for scalable high efficiency video coding, which improves visual quality and coding efficiency through interlayer restoration. By utilizing reconstructed frames from different layers, the network generates interlayers with higher quality, enhancing the coding efficiency.
IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY
(2022)
Article
Environmental Sciences
Jiaping Zhong, Yunsong Li, Weiying Xie, Jie Lei, Xiuping Jia
Summary: In this work, a multi-prior-based network (MPN) is proposed to incorporate well-trained generative adversarial networks (GANs) as effective priors for hyperspectral anomaly detection. By introducing multi-scale covariance maps (MCMs) of precise second-order statistics, multi-scale priors are constructed to reliably and adaptively estimate the HSI label. The network is enhanced with twin least-square loss and a new anomaly rejection loss to improve generative ability and training stability, while establishing a pure and discriminative background estimation.
Article
Environmental Sciences
Jie Lei, Pan Liu, Weiying Xie, Long Gao, Yunsong Li, Qian Du
Summary: This paper proposes a spatial-spectral cross-correlation embedded dual-transfer network (SSDT-Net) for hyperspectral video object tracking, addressing the challenges of limited annotation data and high-dimensional characteristics. Experimental results show that the SSDT-Net offers satisfactory performance with a similar speed to traditional color trackers.
Article
Computer Science, Artificial Intelligence
Tao Jiang, Weiying Xie, Yunsong Li, Jie Lei, Qian Du
Summary: This article proposes a weakly supervised discriminative learning approach using spectral constrained generative adversarial networks for hyperspectral anomaly detection. The network enhances discrimination between anomaly and background, and includes an end-to-end architecture with a novel spectral constraint. Experimental results demonstrate the unique promise of this approach.
IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS
(2022)
Article
Automation & Control Systems
Kai Jiang, Weiying Xie, Jie Lei, Zan Li, Yunsong Li, Tao Jiang, Qian Du
Summary: The study proposes a novel end-to-end local invariant autoencoding density estimation model to address two issues in hyperspectral anomaly target detection: failure to dig out customized features and incapability of preserving inherent information in low-dimensional representation. By introducing a local invariant autoencoder and multidistance measure, more effective anomaly target detection is achieved.
IEEE TRANSACTIONS ON CYBERNETICS
(2022)
Article
Automation & Control Systems
Xin Zhang, Weiying Xie, Yunsong Li, Jie Lei, Qian Du
Summary: This article proposes a novel filter pruning method for deep learning networks by calculating the learned representation median in the frequency domain. The method emphasizes the removal of absolutely unimportant filters and has been shown to outperform existing pruning methods in terms of accuracy and FLOPs reduction.
IEEE TRANSACTIONS ON CYBERNETICS
(2023)
Article
Geochemistry & Geophysics
Jiaqing Zhang, Jie Lei, Weiying Xie, Yunsong Li, Geng Yang, Xiuping Jia
Summary: This paper proposes a guided hybrid quantization with one-to-one self-teaching (GHOST) framework, which combines the synergy of quantization and distillation to achieve a lightweight model. The framework introduces a guided quantization self-distillation (GQSD) structure, a hybrid quantization (HQ) module, and a one-to-one self-teaching (OST) module. Experimental results demonstrate the superiority of the GHOST framework in terms of object detection and lightweight design.
IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING
(2023)
Article
Geochemistry & Geophysics
Jiaqing Zhang, Jie Lei, Weiying Xie, Zhenman Fang, Yunsong Li, Qian Du
Summary: In this article, the authors propose SuperYOLO, an accurate and fast object detection method for remote sensing images. By fusing multimodal data and utilizing assisted super resolution learning, SuperYOLO achieves high-resolution object detection on multiscale objects while considering the computation cost. Experimental results show that SuperYOLO outperforms state-of-the-art models in terms of accuracy and computational efficiency.
IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING
(2023)
Article
Geochemistry & Geophysics
Jie Lei, Simin Xu, Weiying Xie, Jiaqing Zhang, Yunsong Li, Qian Du
Summary: This article introduces a novel method for detecting hyperspectral image (HSI) targets with certain spatial information, referred to as the semantic transferred priori for hyperspectral target detection with spatial-spectral association (SSAD). By using transfer learning, a semantic segmentation network adapted for HSIs is designed to discriminate the spatial areas of targets, and a customized target spectrum is aggregated with those spectral pixels localized. Experiments demonstrate that our proposed method achieves higher detection accuracy and superior visual performance compared to the other benchmark methods.
IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING
(2023)
Article
Geochemistry & Geophysics
Long Gao, Pan Liu, Yan Jiang, Weiying Xie, Jie Lei, Yunsong Li, Qian Du
Summary: In this article, a novel algorithm (CBFF-Net) is proposed for hyperspectral object tracking, aiming to improve discrimination ability and reduce computational complexity. By extracting features from different bands of hyperspectral images and learning inter-band interaction information, the algorithm demonstrates superior performance and runs at a speed of 24 FPS.
IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING
(2023)
Article
Computer Science, Artificial Intelligence
Xin Zhang, Weiying Xie, Yunsong Li, Jie Lei, Kai Jiang, Leyuan Fang, Qian Du
Summary: In this study, a novel model compression method called block-wise partner learning (BPL) is proposed to address the resource limitations faced by convolutional neural networks (CNNs). BPL creates partners for each block during training, evaluates differences using a diversity loss, and fuses the partners equivalently. Experimental results show that BPL outperforms other methods in terms of performance.
IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS
(2023)
Article
Geochemistry & Geophysics
Jie Lei, Yijie Gu, Weiying Xie, Yunsong Li, Qian Du
Summary: This article proposes a boundary extraction constrained Siamese network (BESNet) to improve change detection performance by utilizing boundary information. The BESNet combines traditional and deep learning techniques to maximize their strengths through cooperation. A new boundary extraction constrained loss function and a contractive loss function are used to optimize the network. Experimental results demonstrate that the proposed BESNet significantly improves change detection performance and generates more complete and clearer object boundaries.
IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING
(2022)
Article
Geochemistry & Geophysics
Geng Yang, Jie Lei, Weiying Xie, Zhenman Fang, Yunsong Li, Jiaxuan Wang, Xin Zhang
Summary: In this article, the authors propose OSCAR-RT, an algorithm/hardware codesign framework for real-time on-satellite CNN-based SAR ship detection. OSCAR-RT simultaneously produces an accurate and hardware-friendly CNN model and an ultra-efficient FPGA-based hardware accelerator. Experimental results demonstrate the effectiveness of OSCAR-RT in achieving high detection accuracy and speed for on-satellite ship detection.
IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING
(2022)
Article
Computer Science, Artificial Intelligence
Hamdan Abdellatef, Lina J. Karam
Summary: This paper proposes performing the learning and inference processes in the compressed domain to reduce computational complexity and improve speed of neural networks. Experimental results show that modified ResNet-50 in the compressed domain is 70% faster than traditional spatial-based ResNet-50 while maintaining similar accuracy. Additionally, a preprocessing step with partial encoding is suggested to improve resilience to distortions caused by low-quality encoded images. Training a network with highly compressed data can achieve good classification accuracy with significantly reduced storage requirements.
Article
Computer Science, Artificial Intelligence
Victor R. Barradas, Yasuharu Koike, Nicolas Schweighofer
Summary: Inverse models are essential for human motor learning as they map desired actions to motor commands. The shape of the error surface and the distribution of targets in a task play a crucial role in determining the speed of learning.
Article
Computer Science, Artificial Intelligence
Ting Zhou, Hanshu Yan, Jingfeng Zhang, Lei Liu, Bo Han
Summary: We propose a defense strategy that reduces the success rate of data poisoning attacks in downstream tasks by pre-training a robust foundation model.
Article
Computer Science, Artificial Intelligence
Hao Sun, Li Shen, Qihuang Zhong, Liang Ding, Shixiang Chen, Jingwei Sun, Jing Li, Guangzhong Sun, Dacheng Tao
Summary: In this paper, the convergence rate of AdaSAM in the stochastic non-convex setting is analyzed. Theoretical proof shows that AdaSAM has a linear speedup property and decouples the stochastic gradient steps with the adaptive learning rate and perturbed gradient. Experimental results demonstrate that AdaSAM outperforms other optimizers in terms of performance.
Article
Computer Science, Artificial Intelligence
Juntong Yun, Du Jiang, Li Huang, Bo Tao, Shangchun Liao, Ying Liu, Xin Liu, Gongfa Li, Disi Chen, Baojia Chen
Summary: In this study, a dual manipulator grasping detection model based on the Markov decision process is proposed. By parameterizing the grasping detection model of dual manipulators using a cross entropy convolutional neural network and a full convolutional neural network, stable grasping of complex multiple objects is achieved. Robot grasping experiments were conducted to verify the feasibility and superiority of this method.
Article
Computer Science, Artificial Intelligence
Miaohui Zhang, Kaifang Li, Jianxin Ma, Xile Wang
Summary: This paper proposes an unsupervised person re-identification (Re-ID) method that uses two asymmetric networks to generate pseudo-labels for each other by clustering and updates and optimizes the pseudo-labels through alternate training. It also designs similarity compensation and similarity suppression based on the camera ID of pedestrian images to optimize the similarity measure. Extensive experiments show that the proposed method achieves superior performance compared to state-of-the-art unsupervised person re-identification methods.
Article
Computer Science, Artificial Intelligence
Florian Bacho, Dominique Chu
Summary: This paper proposes a new approach called the Forward Direct Feedback Alignment algorithm for supervised learning in deep neural networks. By combining activity-perturbed forward gradients, direct feedback alignment, and momentum, this method achieves better performance and convergence speed compared to other local alternatives to backpropagation.
Article
Computer Science, Artificial Intelligence
Xiaojian Ding, Yi Li, Shilin Chen
Summary: This research paper addresses the limitations of recursive feature elimination (RFE) and its variants in high-dimensional feature selection tasks. The proposed algorithms, which introduce a novel feature ranking criterion and an optimal feature subset evaluation algorithm, outperform current state-of-the-art methods.
Article
Computer Science, Artificial Intelligence
Naoko Koide-Majima, Shinji Nishimoto, Kei Majima
Summary: Visual images observed by humans can be reconstructed from brain activity, and the visualization of arbitrary natural images from mental imagery has been achieved through an improved method. This study provides a unique tool for directly investigating the subjective contents of the brain.
Article
Computer Science, Artificial Intelligence
Huanjie Tao, Qianyue Duan
Summary: In this paper, a hierarchical attention network with progressive feature fusion is proposed for facial expression recognition (FER), addressing the challenges posed by pose variation, occlusions, and illumination variation. The model achieves enhanced performance by aggregating diverse features and progressively enhancing discriminative features.
Article
Computer Science, Artificial Intelligence
Zhenyi Wang, Pengfei Yang, Linwei Hu, Bowen Zhang, Chengmin Lin, Wenkai Lv, Quan Wang
Summary: In the face of the complex landscape of deep learning, we propose a novel subgraph-level performance prediction method called SLAPP, which combines graph and operator features through an innovative graph neural network called EAGAT, providing accurate performance predictions. In addition, we introduce a mixed loss design with dynamic weight adjustment to improve predictive accuracy.
Article
Computer Science, Artificial Intelligence
Yiyang Yin, Shuangling Luo, Jun Zhou, Liang Kang, Calvin Yu-Chian Chen
Summary: Medical image segmentation is crucial for modern healthcare systems, especially in reducing surgical risks and planning treatments. Transanal total mesorectal excision (TaTME) has become an important method for treating colon and rectum cancers. Real-time instance segmentation during TaTME surgeries can assist surgeons in minimizing risks. However, the dynamic variations in TaTME images pose challenges for accurate instance segmentation.
Article
Computer Science, Artificial Intelligence
Teng Cheng, Lei Sun, Junning Zhang, Jinling Wang, Zhanyang Wei
Summary: This study proposes a scheme that combines the start-stop point signal features for wideband multi-signal detection, called Fast Spectrum-Size Self-Training network (FSSNet). By utilizing start-stop points to build the signal model, this method successfully solves the difficulty of existing deep learning methods in detecting discontinuous signals and achieves satisfactory detection speed.
Article
Computer Science, Artificial Intelligence
Wenming Wu, Xiaoke Ma, Quan Wang, Maoguo Gong, Quanxue Gao
Summary: The layer-specific modules in multi-layer networks are critical for understanding the structure and function of the system. However, existing methods fail to accurately characterize and balance the connectivity and specificity of these modules. To address this issue, a joint learning graph clustering algorithm (DRDF) is proposed, which learns the deep representation and discriminative features of the multi-layer network, and balances the connectivity and specificity of the layer-specific modules through joint learning.
Article
Computer Science, Artificial Intelligence
Guanghui Yue, Guibin Zhuo, Weiqing Yan, Tianwei Zhou, Chang Tang, Peng Yang, Tianfu Wang
Summary: This paper proposes a novel boundary uncertainty aware network (BUNet) for precise and robust colorectal polyp segmentation. BUNet utilizes a pyramid vision transformer encoder to learn multi-scale features and incorporates a boundary exploration module (BEM) and a boundary uncertainty aware module (BUM) to handle boundary areas. Experimental results demonstrate that BUNet outperforms other methods in terms of performance and generalization ability.