检索结果-内蒙古大学图书馆

TransXNet: Learning Both Global and Local Dynamics With a Dual Dynamic Token Mixer for Visual Recognition

IEEE Transactions on Neural Networks and Learning Systems 2025年第6期36卷 11534-11547页

作者： Meng Lou Shu Zhang Hong-Yu Zhou Sibei Yang Chuan Wu Yizhou Yu School of Computing and Data Science The University of Hong Kong Hong Kong SAR China Artificial Intelligence Laboratory Deepwise Healthcare Beijing China Department of Biomedical Informatics Harvard Medical School Boston CA USA Department of Computer Science The University of Hong Kong Hong Kong SAR China School of Information Science and Technology ShanghaiTech University Shanghai China

Recent studies have integrated convolutions into transformers to introduce inductive bias and improve generalization performance. However, the static nature of conventional convolution prevents it from dynamically adapting to input variations, resulting in a representation discrepancy between convolution and self-attention as self-attention calculates attention matrices dynamically. Furthermore, when stacking token mixers that consist of convolution and self-attention to form a deep network, the static nature of convolution hinders the fusion of features previously generated by self-attention into convolution kernels. These two limitations result in a suboptimal representation capacity of the constructed networks. To find a solution, we propose a lightweight dual dynamic token mixer (D-Mixer) to simultaneously learn global and local dynamics, that is, mechanisms that compute weights for aggregating global contexts and local details in an input-dependent manner. D-Mixer works by applying an efficient global attention module and an input-dependent depthwise convolution separately on evenly split feature segments, endowing the network with strong inductive bias and an enlarged effective receptive field. We use D-Mixer as the basic building block to design TransXNet, a novel hybrid CNN–transformer vision backbone network that delivers compelling performance. In the ImageNet-1K image classification task, TransXNet-T surpasses Swin-T by 0.3% in top-1 accuracy while requiring less than half of the computational cost. Furthermore, TransXNet-S and TransXNet-B exhibit excellent model scalability, achieving top-1 accuracy of 83.8% and 84.6%, respectively, with reasonable computational costs. In addition, our proposed network architecture demonstrates strong generalization capabilities in various dense prediction tasks, outperforming other state-of-the-art networks while having lower computational costs. Code is publicly available at https://***/LMMMEng/TransXNet .

关键词： Mixers Transformers Computational modeling Kernel Computational efficiency Feature extraction Convolutional codes Computer vision Accuracy Stacking

来源：评论

学校读者我要写书评

暂无评论

Captions Speak Louder than Images (CASLIE): Generalizing Foundation Models for E-commerce from High-quality Multimodal Instruction data

arXiv

引用

arXiv 2024年

作者： Ling, Xinyi Peng, Bo Du, Hanwen Zhu, Zhihui Ning, Xia Department of Computer Science and Engineering The Ohio State University United States Translational Data Analytics Institute The Ohio State University United States Department of Biomedical Informatics The Ohio State University United States

Leveraging multimodal data to drive breakthroughs in e-commerce applications through Multimodal Foundation Models (MFMs) is gaining increasing attention from the research community. However, there are significant challenges that hinder the optimal use of multimodal e-commerce data by foundation models: (1) the scarcity of large-scale, high-quality multimodal benchmark datasets;and (2) the lack of effective multimodal information integration methods. To address these challenges, in this paper, we introduce MMECInstruct, the first-ever, large-scale, and high-quality multimodal instruction dataset for e-commerce. We also develop CASLIE, a simple, lightweight, yet effective framework for integrating multimodal information for e-commerce. Leveraging MMECInstruct, we fine-tune a series of e-commerce MFMs within CASLIE, denoted as CASLIE models. Our comprehensive evaluation demonstrates that CASLIE models substantially outperform 5 categories of advanced baseline models in the in-domain evaluation. Moreover, CASLIE models show strong generalizability to out-of-domain settings. MMECInstruct and CASLIE models are publicly accessible through https://***/CASLIE/. © 2024, CC BY.

关键词： Large datasets

来源：评论

学校读者我要写书评

暂无评论

Dual Prompting for Diverse Count-Level Pet Denoising

Dual Prompting for Diverse Count-Level Pet Denoising

引用

IEEE International Symposium on biomedical Imaging

作者： Xiaofeng Liu Yongsong Huang Thibault Marin Yanis Chemli Samira Vafay Eslahi Amal Tiss Keith A. Johnson Georges El Fakhri Jinsong Ouyang Dept. of Radiology and Biomedical Imaging Yale University New Haven CT USA Dept. of Biomedical Informatics and Data Science Yale University New Haven CT USA Dept. of Radiology Massachusetts General Hospital and Harvard Medical School Boston MA USA

ISBN: (数字)9798331520526

ISBN: (纸本)9798331520533

The to-be-denoised positron emission tomography (PET) volumes are inherent with diverse count levels, which imposes challenges for a unified model to tackle varied cases. In this work, we resort to the recently flourished prompt learning to achieve generalizable PET denoising with different count levels. Specifically, we propose dual prompts to guide the PET denoising in a divide-and-conquer manner, i.e., an explicitly count-level prompt to provide the specific prior information and an implicitly general denoising prompt to encode the essential PET denoising knowledge. Then, a novel prompt fusion module is developed to unify the heterogeneous prompts, followed by a prompt-feature interaction module to inject prompts into the features. The prompts are able to dynamically guide the noise-conditioned denoising process. Therefore, we are able to efficiently train a unified denoising model for various count levels, and deploy it to different cases with personalized prompts. We evaluated on 1940 low-count PET 3D volumes with uniformly randomly selected 13-22% fractions of events from 97 18F-MK6240 tau PET studies. It shows our dual prompting can largely improve the performance with informed count-level and outperform the count-conditional model.

关键词： Degradation Three-dimensional displays Biological system modeling Noise reduction Image restoration Positron emission tomography Image denoising biomedical imaging

来源：评论

学校读者我要写书评

暂无评论

Network-based Topic Structure Visualization

arXiv

引用

arXiv 2024年

作者： Jeon, Yeseul Park, Jina Jin, Ick Hoon Chung, Dongjun Department of Statistics and Data Science Yonsei University Seoul Korea Republic of Department of Applied Statistics Yonsei University Seoul Korea Republic of Department of Biomedical Informatics The Ohio State University Columbus United States

In the real world, many topics are inter-correlated, making it challenging to investigate their structure and relationships. Understanding the interplay between topics and their relevance can provide valuable insights for researchers, guiding their studies and informing the direction of research. In this paper, we utilize the topic-words distribution, obtained from topic models, as item-response data to model the structure of topics using a latent space item response model. By estimating the latent positions of topics based on their distances toward words, we can capture the underlying topic structure and reveal their relationships. Visualizing the latent positions of topics in Euclidean space allows for an intuitive understanding of their proximity and associations. We interpret relationships among topics by characterizing each topic based on representative words selected using a newly proposed scoring scheme. Additionally, we assess the maturity of topics by tracking their latent positions using different word sets, providing insights into the robustness of topics. To demonstrate the effectiveness of our approach, we analyze the topic composition of COVID-19 studies during the early stage of its emergence using biomedical literature in the PubMed database. The software and data used in this paper are publicly available at https://***/jeon9677/gViz. Copyright © 2024, The Authors. All rights reserved.

关键词： COVID-19

来源：评论

学校读者我要写书评

暂无评论

eCeLLM: Generalizing Large Language Models for E-commerce from Large-scale, High-quality Instruction data

arXiv

引用

arXiv 2024年

作者： Peng, Bo Ling, Xinyi Chen, Ziru Sun, Huan Ning, Xia Department of Computer Science and Engineering The Ohio State University United States Translational Data Analytics Institute The Ohio State University United States Department of Biomedical Informatics The Ohio State University United States

With tremendous efforts in developing effective e-commerce models, conventional e-commerce models show limited success in generalist e-commerce modeling, and suffer from unsatisfactory performance on new users and new products – a typical out-of-domain generalization challenge. Meanwhile, large language models (LLMs) demonstrate outstanding performance in generalist modeling and out-of-domain generalizability in many fields. Toward fully unleashing their power for e-commerce, in this paper, we construct ECInstruct, the first open-sourced, large-scale, and high-quality benchmark instruction dataset for e-commerce. Leveraging ECInstruct, we develop eCeLLM, a series of e-commerce LLMs, by instruction-tuning general-purpose LLMs. Our comprehensive experiments and evaluation demonstrate that eCeLLM models substantially outperform baseline models, including the most advanced GPT-4, and the state-of-the-art task-specific models in in-domain evaluation. Moreover, eCeLLM exhibits excellent generalizability to out-of-domain settings, including unseen products and unseen instructions, highlighting its superiority as a generalist e-commerce model. Both the ECInstruct dataset and the eCeLLM models show great potential in empowering versatile and effective LLMs for e-commerce. ECInstruct and eCeLLM models are publicly accessible through https://***/eCeLLM/. © 2024, CC BY.

关键词： Marketplaces

来源：评论

学校读者我要写书评

暂无评论

Developing a Deep Learning Model Using Transfer Learning from EfficientNet-b3 to Detect Knee Fracture on X-ray Images 23

Developing a Deep Learning Model Using Transfer Learning fro...

引用

7th International Conference on Medical and Health informatics, ICMHI 2023

作者： Huang, Shu-Tien Liu, Liong-Rung Tsai, Ming-Feng Huang, Ming-Yuan Chiu, Hung-Wen Department of Emergency Medicine Mackay Memorial Hospital Taipei Taiwan Graduate Institute of Biomedical Informatics College of Medical Science and Technology Taipei Medical University Taipei City Taiwan Department of Medicine Mackay Medical College New Taipei City Taiwan Clinical Big Data Research Center Taipei Medical University Hospital Taipei City Taiwan

ISBN: (纸本)9798400700712

Conventional radiographs are used for fracture detection routinely in knee injury patients. Miss diagnosis is harmful to patients and stressful to physicians. Thus, a clinical decision support system utilizing a deep neural network should be helpful in preventing physicians from overlooking and also improving patient safety. This study uses a deep learning model (DLM) with transfer learning from EfficientNet-b3 to detect knee fractures on X-ray images. About 12% of the total 13,615 cases were used to test the model. The testing accuracy of the trained model was 90.56%. The area under the receiver operator characteristic curve (AUC) was 0.960. Our findings highlight that the deep learning model can detect knee fractures with remarkable performance. Further implementation into clinical use as a decision support system can be helpful to prevent misdiagnosis and subsequent patient harm. © 2023 ACM.

关键词： Decision support systems

来源：评论

学校读者我要写书评

暂无评论

Quantum variational autoencoder utilizing regularized mixed-state latent representations

引用

Physical Review A 2025年第4期111卷 042416-042416页

作者： Gaoyuan Wang Jonathan Warrell Prashant S. Emani Mark Gerstein Program in Computational Biology and Bioinformatics Yale University New Haven Connecticut 06520 USA Department of Molecular Biophysics and Biochemistry Yale University New Haven Connecticut 06520 USA NEC Laboratories America Princeton New Jersey 08540 USA Department of Computer Science Yale University New Haven Connecticut 06520 USA Department of Statistics & Data Science Yale University New Haven Connecticut 06520 USA Department of Biomedical Informatics & Data Science Yale University New Haven Connecticut 06520 USA

A major challenge in near-term quantum computing is its application to large real-world datasets due to scarce quantum hardware resources. One approach to enabling tractable quantum models for such datasets involves finding low-dimensional representations that preserve essential information for downstream analysis. In classical machine learning, variational autoencoders (VAEs) facilitate efficient data compression, representation learning for subsequent tasks, and novel data generation. However, no quantum model has been proposed that exactly captures all of these features for direct application to quantum data on quantum computers. Some existing quantum models for data compression lack regularization of latent representations, thus preventing direct use for generation and control of generalization. Others are hybrid models with only some internal quantum components, impeding direct training on quantum data. To address this, we present a fully quantum framework, ζ-QVAE, which encompasses all the capabilities of classical VAEs and can be directly applied to map both classical and quantum data to a lower-dimensional space, while effectively reconstructing much of the original state from it. Our model utilizes regularized mixed states to attain optimal latent representations. It accommodates various divergences for reconstruction and regularization. Furthermore, by accommodating mixed states at every stage, it can utilize the full data density matrix and allow for a training objective defined on probabilistic mixtures of input data. Doing so, in turn, makes efficient optimization possible and has potential implications for private and federated learning. In addition to exploring the theoretical properties of ζ-QVAE, we demonstrate its performance on representative genomics and synthetic data. Our results indicate that ζ-QVAE consistently learns representations that better utilize the capacity of the latent space and exhibits similar or better performance compared with

关键词： Quantum computers

来源：评论

学校读者我要写书评

暂无评论

Enhancing Diabetic Retinopathy Screening with Sequential Deep Learning Models

Enhancing Diabetic Retinopathy Screening with Sequential Dee...

引用

International Conference on Image Information Processing

作者： Vankadari Mohith Kalpana Raja I. R. Oviya Department of Computer Science and Engineering (AIE) Amrita School of Computing Amrita Vishwa Vidyapeetham Chennai India Section for Biomedical Informatics and Data Science School of Medicine Yale University New Haven USA

ISBN: (数字)9798350371406

ISBN: (纸本)9798350371413

Diabetic retinopathy is a serious medical disorder that, if left untreated, can result in visual impairment or blindness. The precise and timely categorization of its severity is critical for appropriate medical management. This research describes an automated method for determining the severity of diabetic retinopathy using deep learning algorithms. The suggested methodology adopts a two-step process for identifying diabetic retinopathy and then categorizing its severity. In this technique, two pre-trained deep learning models, InceptionResNetV2 and DenseNet121, are used. For training and assessment purposes, the “APTOS 2019 Blindness Detection” dataset which consists of five severity classes is used as the foundation. To overcome class imbalance, data augmentation approaches are used to improve the model’s performance. The results of the experiment show that the strategy is effective, with an accuracy of 83.10 % and an F1 score of 82.77 %. This study contributes to the development of automated systems for assessing diabetic retinopathy, perhaps enhancing early detection and treatment.

关键词： Deep learning Training Diabetic retinopathy Visual impairment Transfer learning Blindness Information processing

来源：评论

学校读者我要写书评

暂无评论

TX-Phase: Secure Phasing of Private Genomes in a Trusted Execution Environment 29th

TX-Phase: Secure Phasing of Private Genomes in a Trusted ...

引用

29th International Conference on Research in Computational Molecular Biology, RECOMB 2025

作者： Dokmai, Natnatee Zhu, Kaiyuan Sahinalp, S. Cenk Cho, Hyunghoon Department of Biomedical Informatics and Data Science Yale School of Medicine New HavenCT United States Department of Computer Science and Engineering UC San Diego La JollaCA United States Cancer Data Science Laboratory National Cancer Institute National Institutes of Health BethesdaMD United States Department of Computer Science Yale University New HavenCT United States

ISBN: (纸本)9783031902512

Genotype imputation servers enable researchers with limited resources to extract valuable insights from their data with enhanced accuracy and ease. However, the utility of these services is limited for those with sensitive study cohorts or those in restrictive regulatory environments due to data privacy concerns. Although privacy-preserving analysis tools have been developed to broaden access to these servers, none of the existing methods support haplotype phasing, a critical component of the imputation workflow. The complexity of phasing algorithms poses a significant challenge in maintaining practical performance under privacy constraints. Here, we introduce TX-Phase, a secure haplotype phasing method based on the framework of Trusted Execution Environments (TEEs). TX-Phase allows users’ private genomic data to be phased while ensuring data confidentiality and integrity of the computation. We introduce novel data-oblivious algorithmic techniques based on compressed reference panels and dynamic fixed-point arithmetic that comprehensively mitigate side-channel leakages in TEEs to provide robust protection of users’ genomic data throughout the analysis. Our experiments on a range of datasets from the UK Biobank and Haplotype Reference Consortium demonstrate the state-of-the-art phasing accuracy and practical runtimes of TX-Phase. Our work enables secure phasing of private genomes, opening access to large reference genomic datasets for a broader scientific community. Our open-source software is available at https://***/hcholab/txphase. The full manuscript is available at https://***/10.1101/2024.09.16.613301. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Sensitive data

来源：评论

学校读者我要写书评

暂无评论

A Transformer-Based Deep Learning Approach for Fairly Predicting Post-Liver Transplant Risk Factors

arXiv

引用

arXiv 2023年

作者： Li, Can Jiang, Xiaoqian Zhang, Kai Department of Biostatistics and Data Science School of Public Health The University of Texas Health Science Center at Houston HoustonTX United States Department of Health Data Science and Artificial Intelligence McWilliams School of Biomedical Informatics The University of Texas Health Science Center at Houston HoustonTX United States

Liver transplantation is a life-saving procedure for patients with end-stage liver disease. There are two main challenges in liver transplant: finding the best matching patient for a donor and ensuring transplant equity among different subpopulations. The current MELD scoring system evaluates a patient's mortality risk if not receiving an organ within 90 days. However, the donor-patient matching should also consider posttransplant risk factors, such as cardiovascular disease, chronic rejection, etc., which are all common complications after transplant. Accurate prediction of these risk scores remains a significant challenge. In this study, we used predictive models to solve the above challenges. Specifically, we proposed a deep learning model to predict multiple risk factors after a liver transplant. By formulating it as a multi-task learning problem, the proposed deep neural network was trained to simultaneously predict the five posttransplant risks and achieve equal good performance by exploiting task-balancing techniques. We also proposed a novel fairness-achieving algorithm to ensure prediction fairness across different subpopulations. We used electronic health records of 160,360 liver transplant patients, including demographic information, clinical variables, and laboratory values, collected from the liver transplant records of the United States from 1987 to 2018. The model's performance was evaluated using various performance metrics such as AUROC and AUPRC. Our experiment results highlighted the success of our multitask model in achieving task balance while maintaining accuracy. The model significantly reduced the task discrepancy by 39%. Further application of the fairness-achieving algorithm substantially reduced fairness disparity among all sensitive attributes (gender, age group, and race/ethnicity) in each risk factor. It underlined the potency of integrating fairness considerations into the task-balancing framework, ensuring robust and fair predictions

关键词： Forecasting

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：