检索结果-内蒙古大学图书馆

A Novel Conditional Medical Image Generation GAN with Latent Space Optimal Transport

学校读者我要写书评

暂无评论

A Novel Conditional Medical Image Generation GAN with Latent...

Medical Artificial Intelligence (MedAI), IEEE International Conference on

作者： Jun Wang Bohan Lei Xiaoyin Xu Yueting Zhuang Min Zhang School of Software Technology Zhejiang University Ningbo China College of Computer Science & Technology Zhejiang University Hangzhou China College of Biomedical Engineering & Instrument Science Zhejiang University Hangzhou China

Generative adversarial network (GAN) is widely used to augment training set in medical imaging. However, training GANs can be challenging, as they are susceptible to mode collapse. These challenges stem from the fact that deep neural networks can only represent continuous mappings, while in GAN, the generator aims to compute discontinuous transportation maps between the noise distribution and the data distribution. We propose a novel approach that can overcome mode collapse, and in turn, lead to improved capability by GAN to generate specific classes of medical images. Our method starts by mapping the data manifold to the latent space using an autoencoder (AE). Subsequently, we encode the sample labels and integrate them with the latent representations. Next, we employ extended semi-discrete optimal transport (SDOT) mapping, which maps a Gaussian distribution to the empirical latent distribution, thereby generating new latent representations with known labels. Finally, we employ GAN to establish the mapping from the continuous latent distribution induced by the extended SDOT mapping to the real data distribution, generating high-quality images. We conducted extensive experiments on the DermaMNIST and BloodMNIST datasets. The experimental results highlight the exceptional performance of our model in generating images belonging to specified classes.

关键词：

Decoupling anomaly discrimination and representation learning: self-supervised learning for anomaly detection on attributed graph

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Hu, YanMing Chen, Chuan Deng, BoWen Lai, YuJing Lin, Hao Zheng, ZiBin Bian, Jing School of Computer Science and Engineering Sun Yat-sen University Guangzhou China School of Software Engineering Sun Yat-sen University Zhuhai China School of System Science and Engineering Sun Yat-sen University Guangzhou China Merchants Union Consumer Finance Co. Ltd China

Anomaly detection on attributed graphs is a crucial topic for its practical application. Existing methods suffer from semantic mixture and imbalance issue because they mainly focus on anomaly discrimination, ignoring representation learning. It conflicts with the assortativity assumption that anomalous nodes commonly connect with normal nodes directly. Additionally, there are far fewer anomalous nodes than normal nodes, indicating a long-tailed data distribution. To address these challenges, a unique algorithm, Decoupled Self-supervised Learning for Anomaly Detection (DSLAD), is proposed in this paper. DSLAD is a self-supervised method with anomaly discrimination and representation learning decoupled for anomaly detection. DSLAD employs bilinear pooling and masked autoencoder as the anomaly discriminators. By decoupling anomaly discrimination and representation learning, a balanced feature space is constructed, in which nodes are more semantically discriminative, as well as imbalance issue can be resolved. Experiments conducted on various six benchmark datasets reveal the effectiveness of DSLAD. Copyright © 2023, The Authors. All rights reserved.

关键词： Anomaly detection

VIRES: Video Instance Repainting via Sketch and Text Guided Generation

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Weng, Shuchen Zheng, Haojie Zhang, Peixuan Hong, Yuchen Jiang, Han Li, Si Shi, Boxin National Key Laboratory for Multimedia Information Processing School of Computer Science Peking University China National Engineering Research Center of Visual Technology School of Computer Science Peking University China OpenBayes Information Technology Co. Ltd. China School of Software and Microelectronics Peking University China School of Artificial Intelligence Beijing University of Posts and Telecommunications China

We introduce VIRES, a video instance repainting method with sketch and text guidance, enabling video instance repainting, replacement, generation, and removal. Existing approaches struggle with temporal consistency and accurate alignment with the provided sketch sequence. VIRES leverages the generative priors of text-to-video models to maintain temporal consistency and produce visually pleasing results. We propose the Sequential ControlNet with the standardized self-scaling, which effectively extracts structure layouts and adaptively captures high-contrast sketch details. We further augment the diffusion transformer backbone with the sketch attention to interpret and inject fine-grained sketch semantics. A sketch-aware encoder ensures that repainted results are aligned with the provided sketch sequence. Additionally, we contribute the VIRESET, a dataset with detailed annotations tailored for training and evaluating video instance editing methods. Experimental results demonstrate the effectiveness of VIRES, which outperforms state-of-the-art methods in visual quality, temporal consistency, condition alignment, and human ratings. Project page:https://***/projects/VIRES/ Copyright © 2024, The Authors. All rights reserved.

关键词： Video analysis

A Global Opinion-influencing Consensus Model based on the DeGroot

学校读者我要写书评

暂无评论

A Global Opinion-influencing Consensus Model based on the De...

IEEE International Symposium on Parallel and Distributed Processing with Applications and IEEE International Conference on Ubiquitous Computing and Communications (ISPA/IUCC)

作者： Yuntian Zhang Xiaoliang Chen Zexia Huang Xianyong Li Yajun Du School of Computer and Software Engineering Xihua University Chengdu China College of Science Xihua University Chengdu China

Social networks have become an important platform for transmitting and sharing information due to the rapid development of online social networks. Opinion dynamics have been examined through the consensus-reaching process (CRP) in social networks, which aims to model the evolution of opinions in social networks so that agents can reach a consensus. Many researchers have solved the CRP problem by improving the DeGroot model, which models divide agents into two categories, leaders and followers, and change the network structure or the values of the agents’ opinions to bring the network to a consensus. However, all of them require the construction of leaders who can influence the entire network. Consensus cannot be achieved without the leaders. This paper proposes a global opinion-influencing consensus model (GOCM) to solve the CRP problem. A network agent refers not only to the opinion of its neighbors but also to the average opinion of the entire network. The numerical analysis indicates that our proposed GOCM can significantly accelerate the achievement of an expected consensus.

关键词： Analytical models Social networking (online) Numerical analysis Computational modeling Ubiquitous computing Numerical models

FM-FCN:A Neural Network with Filtering Modules for Accurate Vital Signs Extraction

学校读者我要写书评

暂无评论

Research 2025年第1期2024卷 92-106页

作者： Fangfang Zhu Qichao Niu Xiang Li Qi Zhao Honghong Su Jianwei Shuai Department of Physics and Fujian Provincial Key Laboratory for Soft Functional Materials ResearchXiamen UniversityXiamen 361005China National Institute for Data Science in Health and Medicine and State Key Laboratory of Cellular Stress BiologyInnovation Center for Cell Signaling NetworkXiamen UniversityXiamen 361005China Vitalsilicon Technology Co.Ltd. JiaxingZhejiang 314006China School of Computer Science and Software Engineering University of Science and Technology LiaoningAnshan 114051China Yangtze Delta Region Institute of Tsinghua University ZhejiangJiaxing 314006China Wenzhou Institute University of Chinese Academy of SciencesWenzhou 325001China Oujiang Laboratory (Zhejiang Lab for Regenerative Medicine Vision and Brain Health)Wenzhou 325001China

Neural networks excel at capturing local spatial patterns through convolutional modules,but they may struggle to identify and effectively utilize the morphological and amplitude periodic nature of physiological *** this work,we propose a novel network named filtering module fully convolutional network(FM-FCN),which fuses traditional filtering techniques with neural networks to amplify physiological signals and suppress ***,instead of using a fully connected layer,we use an FCN to preserve the time-dimensional correlation information of physiological signals,enabling multiple cycles of signals in the network and providing a basis for signal ***,we introduce the FM as a network module that adapts to eliminate unwanted interference,leveraging the structure of the *** approach builds a bridge between deep learning and signal processing ***,we evaluate the performance of FM-FCN using remote *** results demonstrate that FM-FCN outperforms the second-ranked method in terms of both blood volume pulse(BVP)signal and heart rate(HR)*** substantially improves the quality of BVP waveform reconstruction,with a decrease of 20.23%in mean absolute error(MAE)and an increase of 79.95%in signal-to-noise ratio(SNR).Regarding HR estimation accuracy,FM-FCN achieves a decrease of 35.85%in MAE,29.65%in error standard deviation,and 32.88%decrease in 95%limits of agreement width,meeting clinical standards for HR accuracy *** results highlight its potential in improving the accuracy and reliability of vital sign measurement through high-quality BVP signal *** codes and datasets are available online at https://***/zhaoqi106/FM-FCN.

关键词： physiological signalsin filtering module fully convolutional network fm fcn which vital signs extraction amplify physiological signals convolutional modulesbut neural networks filtering module capturing local spatial patterns

LLGS: Illuminating Gaussian Splatting via absorptance Modulation

学校读者我要写书评

暂无评论

LLGS: Illuminating Gaussian Splatting via absorptance Modula...

International Conference on Acoustics, Speech, and Signal Processing (ICASSP)

作者： Jianwen Gan Wenxin Li Bo Zheng Chengliang Wang Yingbo Wu National Elite Institute of Engineering Chongqing University China AI Lab Chongqing Changan Automobile Co. Ltd. China College of Computer Science Chongqing University China School of Big Data & Software Engineering Chongqing University China

ISBN: (数字)9798350368741

ISBN: (纸本)9798350368758

Low-light images are typically characterized by low pixel intensity and color distortion, presenting a significant challenge for accurate 3D reconstruction with 3D Gaussian Splatting (3DGS). Traditional 2D enhancement methods fail to maintain consistent illumination, affecting reconstruction quality. We propose Low-Light Gaussian (LLGS), which can directly leverage low-light images for 3D reconstruction and synthesizing normal-light novel views. LLGS incorporates absorptance to simulate light behavior in low-light conditions, assuming objects maintain normal illumination while reflected light intensity attenuates due to absorptance during rendering. This approach enables the capture of authentic color information in dimly lit scenes. LLGS outperforms current enhancement algorithms and Neural Radiance Fields (NeRF) in image quality and processing efficiency, making it highly effective for low-light 3D scene reconstruction and novel view synthesis.

关键词： Image quality Three-dimensional displays Image color analysis Lighting Signal processing algorithms Modulation Speech enhancement Neural radiance field Rendering (computer graphics) Image reconstruction

Image super-resolution based on additional self-loop supervision 3

学校读者我要写书评

暂无评论

Image super-resolution based on additional self-loop supervi...

2021 3rd International Conference on Artificial Intelligence and computer science, AICS 2021

作者： Chen, Hong Xu, Li Luo, Bing Du, Shuai Xiao, Kunshu Li, Siwei School of Computer and Software Engineering University of Xihua Chengdu China School of Science University of Xihua Chengdu China Xihua College of Xihua University University of Xihua Chengdu China

Relying on the prevalence of deep neural networks, only one image super-resolution (SR) research has taken a big step forward. Many network models use the difference between the real image and the generated super-resolution image as a loss function, ignoring the difference between the small-scale image and the super-resolution generated image. We adopt an end-to-end network model with two-way supervision, which can ensure that the image content is similar in both large and small scales. Only real natural images are used for supervision. As the scale of the image becomes larger, the difference becomes larger, and the effect of correcting image details becomes smaller. Adding the loss between the input image and the degraded image of the generated image can not only keep the content of the image similar on a small scale, but also ensure the image details. Compared with several state-of-the-arts, our method obtains the best results. © Journal of Physics: Conference Series 2021.

关键词： Deep neural networks

Quantum Privacy-Preserving Price E-Negotiation

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Liu, Wen-Jie Li, Chun-Tang Zheng, Yu Xu, Yong Xu, Yin-Song Jiangsu Engineering Center of Network Monitoring Nanjing University of Information Science & Technology Nanjing210044 China School of Computer and Software Nanjing University of Information Science & Technology Nanjing210044 China

Privacy-preserving price e-negotiation (3PEN) is an important topic of secure multi-party computation (SMC) in the electronic commerce field, and the key point of its security is to guarantee the privacy of seller’s and buyer’s prices. In this study, a novel and efficient quantum solution to the 3PEN problem is proposed, where the oracle operation and the qubit comparator are utilized to obtain the comparative results of buyer’s and seller’s prices, and then quantum counting is executed to summarize the total number of products which meets the trading conditions. Analysis shows that our solution not only guarantees the correctness and the privacy of 3PEN, but also has lower communication complexity than those classical ones. © 2023, CC BY.

关键词： Comparators (optical)

SlideGCD: Slide-based Graph Collaborative Training with Knowledge Distillation for Whole Slide Image Classification

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Shu, Tong Shi, Jun Sun, Dongdong Jiang, Zhiguo Zheng, Yushan School of Computer Science and Information Engineering Hefei University of Technology Hefei230601 China School of Software Hefei University of Technology Hefei230601 China Image Processing Center School of Astronautics Beihang University Beijing102206 China School of Engineering Medicine Beijing Advanced Innovation Center on Biomedical Engineering Beihang University Beijing100191 China

Existing WSI analysis methods lie on the consensus that histopathological characteristics of tumors are significant guidance for cancer diagnostics. Particularly, as the evolution of cancers is a continuous process, the correlations and differences across various stages, anatomical locations and patients should be taken into account. However, recent research mainly focuses on the inner-contextual information in a single WSI, ignoring the correlations between slides. To verify whether introducing the slide inter-correlations can bring improvements to WSI representation learning, we propose a generic WSI analysis pipeline SlideGCD that considers the existing multi-instance learning (MIL) methods as the backbone and forge the WSI classification task as a node classification problem. More specifically, SlideGCD declares a node buffer that stores previous slide embeddings for subsequent extensive slide-based graph construction and conducts graph learning to explore the inter-correlations implied in the slide-based graph. Moreover, we frame the MIL classifier and graph learning into two parallel work-flows and deploy the knowledge distillation to transfer the differentiable information to the graph neural network. The consistent performance boosting, brought by SlideGCD, of four previous state-of-the-art MIL methods is observed on two TCGA benchmark datasets. The code is available at https://***/HFUT-miaLab/SlideGCD. Copyright © 2024, The Authors. All rights reserved.

关键词： Classification (of information)