检索结果-内蒙古大学图书馆

Decomposed Neural Architecture Search for image denoising

学校读者我要写书评

暂无评论

Applied Soft Computing 2022年 124卷

作者： Li, Di Bai, Yunpeng Bai, Zongwen Li, Ying Shang, Changjing Shen, Qiang School of Computer Science National Engineering Laboratory for Integrated Aero-Space-Ground-Ocean Big Data Application Technology Shaanxi Provincial Key Laboratory of Speech & Image Information Processing Northwestern Polytechnical University Xi'an710129 China Department of Computer Science Faculty of Business and Physical Sciences Aberystwyth University AberystwythSY233DB United Kingdom Shaanxi Key Laboratory of Intelligent Processing for Big Energy Data School of Physics and Electronic Information Yan'an University Yan'an716000 China

In practical applications of deep learning, as the demand for the modeling capability increases, the network size may need to be massively enlarged in response. This may form a significant challenge in practice, especially when facing the dilemma of limited computational resources, making model compression indispensable. It can be time-consuming and interminable to obtain an appropriate network architecture through manual compression. In this paper, we propose an automated method for searching decomposed network architectures, named DNAS (standing for Decomposed Neural Architecture Search). It integrates both tasks of neural architecture search and tensor decomposition based model compression within a unified framework. The method is able to efficiently find a compact network with high performance for image denoising, with respect to memory and runtime. Particularly, using one single V100 GPU, it only takes about 1.5 h to obtain a denoising network on the BSD500 dataset. Experimental results demonstrate that compared with models developed using existing methods, DNAS consumes significantly less inference time and employs much fewer trainable parameters, outperforming existing approaches on both synthetic and real-world denoising datasets. © 2022 Elsevier B.V.

关键词： Network architecture

Learning Hierarchical Graph Representation for image Manipulation Detection

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Pan, Wenyan Zhou, Zhili Ling, Miaogen Geng, Xin Wu, Q.M. Jonathan School of Computer and Software & Engineering Research Center of Digital Forensics Ministry of Education Nanjing University of Information Science and Technology Nanjing China Provincial Key Laboratory for Computer Information Processing Technology Soochow University Suzhou China School of Computer Science and Engineering Southeast University Nanjing China Department of Electrical and Computer Engineering University of Windsor WindsorON Canada

The objective of image manipulation detection is to identify and locate the manipulated regions in the images. Recent approaches mostly adopt the sophisticated Convolutional Neural Networks (CNNs) to capture the tampering artifacts left in the images to locate the manipulated regions. However, these approaches ignore the feature correlations, i.e., feature inconsistencies, between manipulated regions and non-manipulated regions, leading to inferior detection performance. To address this issue, we propose a hierarchical Graph Convolutional Network (HGCN-Net), which consists of two parallel branches: the backbone network branch and the hierarchical graph representation learning (HGRL) branch for image manipulation detection. Specifically, the feature maps of a given image are extracted by the backbone network branch, and then the feature correlations within the feature maps are modeled as a set of fully-connected graphs for learning the hierarchical graph representation by the HGRL branch. The learned hierarchical graph representation can sufficiently capture the feature correlations across different scales, and thus it provides high discriminability for distinguishing manipulated and non-manipulated regions. Extensive experiments on four public datasets demonstrate that the proposed HGCN-Net not only provides promising detection accuracy, but also achieves strong robustness under a variety of common image attacks in the task of image manipulation detection, compared to the state-of-the-arts. Copyright © 2022, The Authors. All rights reserved.

关键词： Convolutional neural networks

Report-Guided Cross-Modal Representation Learning for Predicting EGFR Mutations by Whole Slide image

学校读者我要写书评

暂无评论

Report-Guided Cross-Modal Representation Learning for Predic...

IEEE International Conference on Bioinformatics and Biomedicine (BIBM)

作者： Qi Qiao Jun Shi Zhiguo Jiang Wei Wang Haibo Wu Yushan Zheng School of Computer Science and Information Engineering Hefei University of Technology Hefei China School of Software Hefei University of Technology Hefei China Image Processing Center School of Astronautics Beihang University Beijing China Department of Pathology the First Affiliated Hospital of USTC Division of Life Sciences and Medicine University of Science and Technology of China Hefei China Intelligent Pathology Institute Division of Life Sciences and Medicine University of Science and Technology of China Hefei China School of Engineering Medicine Beijing Advanced Innovation Center for Biomedical Engineering Beihang University Beijing China

ISBN: (数字)9798350386226

ISBN: (纸本)9798350386233

Traditional PCR/NGS-based multigene panel testing is time-consuming and costly. Predicting EGFR mutations directly from H&E stained whole slide images (WSIs) can alleviate these limitations. Furthermore, histopathological reports contain valuable textual information that correlates with tissue areas in WSIs. However, recent research mainly analyses EGFR mutation status only from a single modality, ignoring rich information contained in reports. In this paper, we propose a report-guided cross-modal representation learning method for predicting EGFR mutations by WSIs. Specifically, we reconstruct report-level embeddings through exploring intrinsic relationships between diagnostic words in histopathological reports and tissue areas in WSIs. Finally, reconstructed histopathological report embedding and aggregated WSI embedding are fused for final prediction. More importantly, molecular testing report is also introduced as prior supervision information at the training stage to guarantee semantic consistency of fused feature and molecular report embedding. We evaluate our method on the TCGA-EGFR public benchmark dataset and an in-house clinical dataset (USTC-EGFR). Experimental results demonstrate that our method outperforms existing approaches in EGFR mutation prediction, highlighting the benefits of cross-modal learning in enhancing feature representational ability. The code is available at https://***/HFUT-miaLab/RCRL.

关键词： Representation learning Training Codes Supervised learning Semantics Medical treatment Benchmark testing Bioinformatics image reconstruction Biomedical imaging

Deep Learning-Based Diffusion MRI Tractography: Integrating Spatial and Anatomical Information

学校读者我要写书评

暂无评论

arXiv 2025年

作者： Yang, Yiqiong Yuan, Yitian Ren, Baoxing Wu, Ye Feng, Yanqiu Zhang, Xinyuan School of Biomedical Engineering Southern Medical University Guangzhou510515 China Guangdong Provincial Key Laboratory of Medical Image Processing Guangdong Province Engineering Laboratory for Medical Imaging and Diagnostic Technology Southern Medical University Guangzhou510515 China School of Computer Science and Technology Nanjing University of Science and Technology Nanjing China Guangdong-Hong Kong-Macao Greater Bay Area Center for Brain Science and Brain-Inspired Intelligence & Key Laboratory of Mental Health The Ministry of Education Southern Medical University Guangzhou China Department of Radiology Shunde Hospital Southern Medical University The First People's Hospital of Shunde Foshan Foshan China

Diffusion MRI tractography technique enables non-invasive visualization of the white matter pathways in the brain. It plays a crucial role in neuroscience and clinical fields by facilitating the study of brain connectivity and neurological disorders. However, the accuracy of reconstructed tractograms has been a longstanding challenge. Recently, deep learning methods have been applied to improve tractograms for better white matter coverage, but often comes at the expense of generating excessive false-positive connections. This is largely due to their reliance on local information to predict long-range streamlines. To improve the accuracy of streamline propagation predictions, we introduce a novel deep learning framework that integrates image-domain spatial information and anatomical information along tracts, with the former extracted through convolutional layers and the later modeled via a Transformer-decoder. Additionally, we employ a weighted loss function to address fiber class imbalance encountered during training. We evaluate the proposed method on the simulated ISMRM 2015 Tractography Challenge dataset, achieving a valid streamline rate of 66.2%, white matter coverage of 63.8%, and successfully reconstructing 24 out of 25 bundles. Furthermore, on the multi-site Tractoinferno dataset, the proposed method demonstrates its ability to handle various diffusion MRI acquisition schemes, achieving a 5.7% increase in white matter coverage and a 4.1% decrease in overreach compared to RNN-based methods. Copyright © 2025, The Authors. All rights reserved.

关键词： image enhancement

Feature-Consistent Cyclic Domain Adversarial Network for Unsupervised Transfer Diagnosis of the Autoimmune Disease Igg4-Rd by Raman Spectroscopy

学校读者我要写书评

暂无评论

SSRN

SSRN 2025年

作者： Zhang, Ziyang Chen, Cheng Qin, Wentao Wu, Xue Liu, Yang Wu, Lijun Lv, Xiaoyi Chang, Chenjie Chen, Xinya Chen, Zhiyuan Xu, Qianxi Li, Zhuoyu Ma, Mengsi Chen, Chen Xinjiang University College of Software Urumqi830046 China Xinjiang Cloud Computing Application Laboratory Xinjiang University Karamay834099 China School of Computer Science and Technology Xinjiang University Urumqi830046 China Key Laboratory of signal detection and processing Xinjiang University Urumqi830046 China Department of Rheumatology＆Immunology People's Hospital of Xinjiang Uygur Autonomous Region Xinjiang Urumqi China Xinjiang Clinical Research Center for Rheumatoid arthritis Xinjiang Urumqi China

Abstracts IgG4-related disease (IgG4-RD) is a multi-organ immune disorder characterized by systemic involvement, diverse pathogenesis, and rarity, which complicates its diagnosis. Traditional medical diagnostic models, predominantly based on supervised learning in machine learning or deep learning frameworks, struggle to address the scarcity of labeled data due to the diagnostic challenges of IgG4-RD. To overcome this limitation, this study proposes a novel framework based on Feature-Consistent Cyclic Domain Adversarial Networks (FCCDAN). The framework first trains a classification model on the source domain for diagnosing source domain diseases under supervised conditions. Subsequently, leveraging the source domain model, the encoder is guided to extract semantic features, while feature consistency loss is integrated into both the generator and discriminator to align the semantic features of the target domain with those of the source domain. Finally, the aligned features are processed through a pre-trained linear mapping to achieve unsupervised classification and diagnosis in the target domain. The proposed model utilizes common autoimmune diseases as a knowledge source, enabling unsupervised transfer diagnosis for IgG4-RD, and demonstrates generalizability through experiments on other disease datasets, achieving an average diagnostic accuracy of 90.62%. This represents improvements of 4.14%, 9.82%, and 10.51% over baseline models, respectively. FCCDAN expands the applicability of Raman spectroscopy in disease diagnosis, maintaining high performance even in label-scarce environments. The overall research workflow also establishes a robust paradigm for the application and advancement of domain adaptation techniques in this context. © 2025, The Authors. All rights reserved.

关键词： Adversarial machine learning

Heterogeneous Laplace Distribution Noise Background Modeling for Sperm Detection in Microscopic images

学校读者我要写书评

暂无评论

Heterogeneous Laplace Distribution Noise Background Modeling...

International Conference on computer and Communications (ICCC)

作者： Manqing Tian Yang Zhao Ni Zeng Xiaomei Kang Jihong Pei Xuan Yang Guangdong Key Laboratory of Intelligent Information Processing College of Electronics and Information Engineering Shenzhen University Shenzhen China College of Computer Science and Software Engineering Shenzhen University Shenzhen China Department of Reproductive Maternal and Child Health Hospital of Hubei Province Tongji Medical College Huazhong University of Science and Technology Wuhan China

Semen quality assessment is a very important tool for the timely detection and treatment of infertility disorders. Many artificial intelligence methods for sperm image analysis have emerged in recent years. Sperm detection in sperm microscopy is the first step in semen quality assessment. However, the acquisition of sperm electron microscopy images can produce a variety of different background lighting situations. The performance of established methods is susceptible to changes in background illumination. Therefore, a sperm detection method with heterogeneous Laplacian distribution noise background modeling (HLDNBM) is proposed. In this paper the method uses background illumination surface fitting to eliminate the effect of illumination in a single sperm image, and realizes the segmentation of sperm head and sperm tail with different grayscale by upper and lower segmentation threshold surfaces to achieve complete sperm image segmentation and multi-target detection in a single image. This method effectively avoids the degradation of target detection performance caused by sudden changes in illumination in other background modeling methods. Moreover, this method shows strong adaptability for images with different lighting backgrounds, and is friendly to small datasets as well. The experimental results show that the accuracy and sensitivity of the algorithm for sperm detection in images with different grayscale characteristics are very promising, with high universality and robustness.

关键词：

Depth-Aware Multi-Modal Fusion for Generalized Zero-Shot Learning

学校读者我要写书评

暂无评论

Depth-Aware Multi-Modal Fusion for Generalized Zero-Shot Lea...

IEEE International Conference on Industrial Informatics (INDIN)

作者： Weipeng Cao Xuyang Yao Zhiwu Xu Yinghui Pan Yixuan Sun Dachuan Li Bohua Qiu Muheng Wei Guangdong Laboratory of Artificial Intelligence and Digital Economy (Shenzhen) Shenzhen China National Engineering Laboratory for Big Data System Computing Technology Shenzhen University Shenzhen China College of Computer Science and Software Engineering Shenzhen University Shenzhen China Stony Brook University New York United States Research Institute of Trustworthy Autonomous Systems Southern University of Science and Technology Shenzhen China Department of Computer Science and Engineering Southern University of Science and Technology Shenzhen China ZhenDui Industry Artificial Intelligence Co. Ltd Shenzhen China Department of Automation Shanghai Jiao Tong University Shanghai China Key Laboratory of System Control and Information Processing Ministry of Education of China Shanghai China

ISBN: (数字)9798331527471

ISBN: (纸本)9798331527488

Realizing Generalized Zero-Shot Learning (GZSL) based on large models is emerging as a prevailing trend. However, most existing methods merely regard large models as black boxes, solely leveraging the features output by the final layer while disregarding potential performance enhancements from other layers. Indeed, numerous researchers have visually depicted variations in the features learned across different layers of neural networks. Motivated by this observation, we propose a Vision Transformer (ViT)-based GZSL method named Depth-Aware Multi-Modal ViT (DAM2ViT), which exploits multi-level features of ViT. DAM2ViT incorporates a multi-modal interaction block to align semantic information of categories across multiple layers, thereby augmenting the model's capacity to learn associations between visual and semantic spaces. Extensive experiments conducted on three benchmark datasets (i.e., CUB, SUN, AWA2) have showcased that DAM2ViT achieves competitive results compared to state-of-the-art methods.

关键词： Visualization Adaptation models Semantics Zero shot learning Neural networks Termination of employment Transformers Market research Sun Optimization

TCEIP: Text Condition Embedded Regression Network for Dental Implant Position Prediction

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Yang, Xinquan Xie, Jinheng Li, Xuguang Li, Xuechen Li, Xin Shen, Linlin Deng, Yongqiang College of Computer Science and Software Engineering Shenzhen University Shenzhen China AI Research Center for Medical Image Analysis and Diagnosis Shenzhen University Shenzhen China National Engineering Laboratory for Big Data System Computing Technology Shenzhen University China Department of Stomatology Shenzhen University General Hospital Shenzhen China National University of Singapore Singapore

When deep neural network has been proposed to assist the dentist in designing the location of dental implant, most of them are targeting simple cases where only one missing tooth is available. As a result, literature works do not work well when there are multiple missing teeth and easily generate false predictions when the teeth are sparsely distributed. In this paper, we are trying to integrate a weak supervision text, the target region, to the implant position regression network, to address above issues. We propose a text condition embedded implant position regression network (TCEIP), to embed the text condition into the encoder-decoder framework for improvement of the regression performance. A cross-modal interaction that consists of cross-modal attention (CMA) and knowledge alignment module (KAM) is proposed to facilitate the interaction between features of images and texts. The CMA module performs a cross-attention between the image feature and the text condition, and the KAM mitigates the knowledge gap between the image feature and the image encoder of the CLIP. Extensive experiments on a dental implant dataset through five-fold cross-validation demonstrated that the proposed TCEIP achieves superior performance than existing methods. Copyright © 2023, The Authors. All rights reserved.

关键词： Signal encoding

An effective coaxiality measurement for twist drill based on line structured light sensor

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Cheng, Ailing Ye, Jiaojiao Yang, Fei Lu, Shufang Gao, Fei The Laboratory of Graphics & Image Processing College of Computer Science and Technology Zhejiang University of Technology Zhejiang Province Hangzhou310023 China The Research Center of Intelligent Computing Software Zhejiang Lab. Zhejiang Province Hangzhou311121 China

Aiming at the accurate and effective coaxiality measurement for twist drill with irregular surface, an optical measurement mechanism is proposed in this paper. First, A high-precision rotation instrument based on four core units is designed, which can obtain the 3-D point cloud data of full angle for the twist drill. Second, in the data processing stage, an improved robust Gaussian mixture model is established for accurate and rapid blade back segmentation. To improve measurement efficiency, a rapid reconstruction method of the twist drill axis based on orthogonal synthesis is provided to locate the axial position of the maximum deviation from the benchmark by utilizing the extracted blade back data. Finally, by calculating the maximum radial Euclidean distance from the benchmark, the coaxiality error of the twist drill is obtained. Comparing with other measurement methods, experimental results show that our proposed method is effective with high precision of 3 um and high efficiency of less than 3 s/pc. The result demonstrate that the proposed method is effective, robust and automatic, it can be applied in many actual industrial scene. © 2021, CC BY.

关键词： Drills