检索结果-内蒙古大学图书馆

CFL-Net: Image Forgery Localization Using Contrastive Learning

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Niloy, Fahim Faisal Bhaumik, Kishor Kumar Woo, Simon S. Center for Computational & Data Sciences Independent University Bangladesh Computer Science and Engineering Department Sungkyunkwan University Suwon Korea Republic of

Conventional forgery localizing methods usually rely on different forgery footprints such as JPEG artifacts, edge inconsistency, camera noise, etc., with cross-entropy loss to locate manipulated regions. However, these methods have the disadvantage of over-fitting and focusing on only a few specific forgery footprints. On the other hand, real-life manipulated images are generated via a wide variety of forgery operations and thus, leave behind a wide variety of forgery footprints. Therefore, we need a more general approach for image forgery localization that can work well on a variety of forgery conditions. A key assumption in underlying forged region localization is that there remains a difference of feature distribution between untampered and manipulated regions in each forged image sample, irrespective of the forgery type. In this paper, we aim to leverage this difference of feature distribution to aid in image forgery localization. Specifically, we use contrastive loss to learn mapping into a feature space where the features between untampered and manipulated regions are well-separated for each image. Also, our method has the advantage of localizing manipulated region without requiring any prior knowledge or assumption about the forgery type. We demonstrate that our work outperforms several existing methods on three benchmark image manipulation datasets. Code is available at https://***/niloy193/CFLNet. © 2022, CC BY.

关键词：

AstroMLab 3: Achieving GPT-4o Level Performance in Astronomy with a Specialized 8B-Parameter Large Language Model

学校读者我要写书评

暂无评论

arXiv 2024年

作者： de Haan, Tijmen Ting, Yuan-Sen Ghosal, Tirthankar Nguyen, Tuan Dung Accomazzi, Alberto Wells, Azton Ramachandra, Nesar Pan, Rui Sun, Zechang Ibaraki Tsukuba Japan Department of Astronomy The Ohio State University ColumbusOH United States The Ohio State University ColumbusOH United States National Center for Computational Sciences Oak Ridge National Laboratory Oak RidgeTN United States Department of Computer and Information Science University of Pennsylvania PhiladelphiaPA United States Center for Astrophysics Harvard & Smithsonian CambridgeMA United States Computational Science Division Argonne National Laboratory LemontIL United States Department of Computer Science and Engineering Hong Kong University of Science and Technology Kowloon Hong Kong Department of Astronomy Tsinghua University Beijing China

AstroSage-Llama-3.1-8B is a domain-specialized natural-language AI assistant tailored for research in astronomy, astrophysics, and cosmology. Trained on the complete collection of astronomy-related arXiv papers from 2007-2024 along with millions of synthetically-generated question-answer pairs and other astronomical literature, AstroSage-Llama-3.1-8B demonstrates remarkable proficiency on a wide range of questions. AstroSage-Llama-3.1-8B scores 80.9% on the AstroMLab-1 benchmark, greatly outperforming all models—proprietary and open-weight—in the 8-billion parameter class, and performing on par with GPT-4o. This achievement demonstrates the potential of domain specialization in AI, suggesting that focused training can yield capabilities exceeding those of much larger, general-purpose models. AstroSage-Llama-3.1-8B is freely available, enabling widespread access to advanced AI capabilities for astronomical education and research. © 2024, CC BY.

关键词： Cosmology

RecurPocket: Recurrent Lmser Network with Gating Mechanism for Protein Binding Site Detection

学校读者我要写书评

暂无评论

RecurPocket: Recurrent Lmser Network with Gating Mechanism f...

IEEE International Conference on Bioinformatics and Biomedicine (BIBM)

作者： Peiying Li Boheng Cao Shikui Tu Lei Xu Department of Computer Science and Engineering Center for Cognitive Machines and Computational Health (CMaCH) Shanghai Jiao Tong University Shanghai China

ISBN: (数字)9781665468190

ISBN: (纸本)9781665468206

It is an essential step to locate the binding sites or pockets of drug molecules on protein structure in drug design. This is challenging because the 3D protein structures are usually in complicated, irregular shape and the pockets are relatively small. Existing deep learning methods for this task are U-Net models, and they have forward skip connections to efficiently transfer features of different levels of 3D structure from encoder to decoder for improving pocket prediction. However, there is still room to improve prediction accuracy. In this paper, we propose RecurPocket, a recurrent Lmser (Least mean square error reconstruction) network for pocket detection. A gated recurrent refinement is devised in RecurPocket to enhance the representation learning on the 3D protein structures. This is fulfilled by feedback connections in RecurPocket network from decoder to encoder, recurrently and progressively improving the feature embedding for accurate prediction. Moreover, a 3D gate mechanism filters out irrelevant information through the feedback links that interfere with detection, making the prediction more precise and clear. Experiments show that RecurPocket improves by 3%-9% on top-n prediction compared with previous state-of-the-art on five benchmark data sets. The source code and trained model are available at https://*** CMACH508/RecurPocket.

关键词： Proteins Representation learning Drugs Protein engineering Solid modeling Three-dimensional displays Source coding

Optimizing Transmit Field Inhomogeneity of Parallel RF Transmit Design in 7T MRI using Deep Learning

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Lu, Zhengyi Liang, Hao Wang, Xiao Yan, Xinqiang Huo, Yuankai Department of Electrical and Computer Engineering Vanderbilt University NashvilleTN United States Vanderbilt University Institute of Imaging Science Vanderbilt University Medical Center NashvilleTN United States Department of Radiology and Radiological Sciences Vanderbilt University Medical Center NashvilleTN United States Computational Science and Engineering Division Oak Ridge National Laboratory Oak RidgeTN United States Department of Computer Science Vanderbilt University NashvilleTN United States

Ultrahigh field (UHF) Magnetic Resonance Imaging (MRI) provides a higher signal-to-noise ratio and, thereby, higher spatial resolution. However, UHF MRI introduces challenges such as transmit radiofrequency (RF) field (B1+) inhomogeneities, leading to uneven flip angles and image intensity anomalies. These issues can significantly degrade imaging quality and its medical applications. This study addresses B1+ field homogeneity through a novel deep learning-based strategy. Traditional methods like Magnitude Least Squares (MLS) optimization have been effective but are time-consuming and dependent on the patient’s presence. Recent machine learning approaches, such as RF Shim Prediction by Iteratively Projected Ridge Regression and deep learning frameworks, have shown promise but face limitations like extensive training times and oversimplified architectures. We propose a two-step deep learning strategy. First, we obtain the desired reference RF shimming weights from multi-channel B1+ fields using random-initialized Adaptive Moment Estimation. Then, we employ Residual Networks (ResNets) to train a model that maps B1+ fields to target RF shimming outputs. Our approach does not rely on pre-calculated reference optimizations for the testing process and efficiently learns residual functions. Comparative studies with traditional MLS optimization demonstrate our method’s advantages in terms of speed and accuracy. The proposed strategy achieves a faster and more efficient RF shimming design, significantly improving imaging quality at UHF. This advancement holds potential for broader applications in medical imaging and diagnostics. Copyright © 2024, The Authors. All rights reserved.

关键词： Magnetic resonance imaging

A Scalable Training-Free Diffusion Model for Uncertainty Quantification

学校读者我要写书评

暂无评论

A Scalable Training-Free Diffusion Model for Uncertainty Qua...

High Performance Computing, Networking, Storage and Analysis, SC-W: Workshops of the International Conference for

作者： Ali Haisam Muhammad Rafid Junqi Yin Yuwei Geng Siming Liang Feng Bao Lili Ju Guannan Zhang Department of Computer Science Virginia Polytechnic Institute and State University Blacksburg VA USA Oak Ridge National Laboratory National Center of Computational Science Oak Ridge TN USA Department of Mathematics University of South Carolina Columbia SC USA Department of Mathematics Florida State University Tallahassee FL USA Computer Science and Math Division Oak Ridge National Laboratory Oak Ridge TN USA

ISBN: (数字)9798350355543

ISBN: (纸本)9798350355550

Generative artificial intelligence extends beyond its success in image/text synthesis, proving itself a powerful uncertainty quantification (UQ) technique through its capability to sample from complex high-dimensional probability distributions. However, existing methods often require a complicated training process, which greatly hinders their applications to real-world UQ problems, especially in dynamic UQ tasks where the target probability distribution evolves rapidly with time. To alleviate this challenge, we have developed a scalable, training-free score-based diffusion model for high-dimensional sampling. We incorporate a parallel-in-time method into our diffusion model to use a large number of GPUs to solve the backward stochastic differential equation and generate new samples of the target distribution. Moreover, we also distribute the computation of the large matrix subtraction used by the training-free score estimator onto multiple GPUs available across all nodes. Compared to existing methods, our approach completely avoids training the score function, making it capable of adapting to rapid changes in the target probability distribution. We showcase the remarkable strong and weak scaling capabilities of the proposed method on the Frontier supercomputer, as well as its uncertainty reduction capability in hurricane predictions when coupled with AI-based foundation models.

关键词： Training Adaptation models Uncertainty Scalability Stochastic processes Diffusion models Probability distribution Supercomputers Hurricanes Load modeling

Transcription Factor-Centric Approach to Identify Non-recurring Putative Regulatory Drivers in Cancer 26th

学校读者我要写书评

暂无评论

Transcription Factor-Centric Approach to Identify Non-recur...

26th International Conference on Research in computational Molecular Biology, RECOMB 2022

作者： Zhao, Jingkang Martin, Vincentius Gordân, Raluca Center for Genomic and Computational Biology Duke University DurhamNC27708 United States Program in Computational Biology and Bioinformatics Duke University DurhamNC27708 United States Department of Computer Science Duke University DurhamNC27708 United States Department of Biostatistics and Bioinformatics Duke University DurhamNC27708 United States Department of Molecular Genetics and Microbiology Duke University DurhamNC27708 United States

ISBN: (纸本)9783031047480

Recent efforts to sequence the genomes of thousands of matched normal-tumor samples have led to the identification of millions of somatic mutations, the majority of which are non-coding. Most of these mutations are believed to be passengers, but a small number of non-coding mutations could contribute to tumor initiation or progression, e.g. by leading to dysregulation of gene expression. Efforts to identify putative regulatory drivers rely primarily on information about the recurrence of mutations across tumor samples. However, in regulatory regions of the genome, individual mutations are rarely seen in more than one donor. Instead of using recurrence information, here we present a method to prioritize putative regulatory driver mutations based on the magnitude of their effects on transcription factor-DNA binding. For each gene, we integrate the effects of mutations across all its regulatory regions, and we ask whether these effects are larger than expected by chance, given the mutation spectra observed in regulatory DNA in the cohort of interest. We applied our approach to analyze mutations in a liver cancer data set with ample somatic mutation and gene expression data available. By combining the effects of mutations across all regulatory regions of each gene, we identified dozens of genes whose regulation in tumor cells is likely to be significantly perturbed by non-coding mutations. Overall, our results show that focusing on the functional effects of non-coding mutations, rather than their recurrence, has the potential to prioritize putative regulatory drivers and the genes they dysregulate in tumor cells. © 2022, The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： Transcription factors

Estimation of continuous environments by robot swarms: Correlated networks and decision-making

学校读者我要写书评

暂无评论

Estimation of continuous environments by robot swarms: Corre...

IEEE International Conference on Robotics and Automation (ICRA)

作者： Mohsen Raoufi Pawel Romanczuk Heiko Hamann Science of Intelligence Research Cluster of Excellence Berlin Germany Department of Biology Institute for Theoretical Biology Humboldt Universität zu Berlin Berlin Germany Department of Electrical Engineering and Computer Science Technical University of Berlin Berlin Germany Bernstein Center for Computational Neuro-science Berlin Germany Department of Computer and Information Science University of Konstanz Konstanz Germany

Collective decision-making is an essential capability of large-scale multi-robot systems to establish autonomy on the swarm level. A large portion of literature on collective decision-making in swarm robotics focuses on discrete decisions selecting from a limited number of options. Here we assign a decentralized robot system with the task of exploring an unbounded environment, finding consensus on the mean of a measurable environmental feature, and aggregating at areas where that value is measured (e.g., a contour line). A unique quality of this task is a causal loop between the robots' dynamic network topology and their decision-making. For example, the network's mean node degree influences time to convergence while the currently agreed-on mean value influences the swarm's aggregation location, hence, also the network structure as well as the precision error. We propose a control algorithm and study it in real-world robot swarm experiments in different environments. We show that our approach is effective and achieves higher precision than a control experiment. We anticipate applications, for example, in containing pollution with surface vehicles.

关键词：

Hyperbolic Secant Representation of the Logistic Function: Application to Probabilistic Multiple Instance Learning for CT Intracranial Hemorrhage Detection

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Castro-Macías, Francisco M. Morales-Álvarez, Pablo Wu, Yunan Molina, Rafael Katsaggelos, Aggelos K. Department of Computer Science and Artificial Intelligence University of Granada Spain Research Centre for Information and Communication Technologies University of Granada Spain Department of Statistics and Operations Research University of Granada Spain Department of Electrical and Computer Engineering Northwestern University United States Center for Computational Imaging and Signal Analytics in Medicine Northwestern University United States

Multiple Instance Learning (MIL) is a weakly supervised paradigm that has been successfully applied to many different scientific areas and is particularly well suited to medical imaging. Probabilistic MIL methods, and more specifically Gaussian Processes (GPs), have achieved excellent results due to their high expressiveness and uncertainty quantification capabilities. One of the most successful GP-based MIL methods, VGPMIL, resorts to a variational bound to handle the intractability of the logistic function. Here, we formulate VGPMIL using Pólya-Gamma random variables. This approach yields the same variational posterior approximations as the original VGPMIL, which is a consequence of the two representations that the Hyperbolic Secant distribution admits. This leads us to propose a general GP-based MIL method that takes different forms by simply leveraging distributions other than the Hyperbolic Secant one. Using the Gamma distribution we arrive at a new approach that obtains competitive or superior predictive performance and efficiency. This is validated in a comprehensive experimental study including one synthetic MIL dataset, two well-known MIL benchmarks, and a real-world medical problem. We expect that this work provides useful ideas beyond MIL that can foster further research in the field. © 2024, CC BY.

关键词： Medical imaging

Can Automated Metadata Extraction Make Scientific Data More Navigable?

学校读者我要写书评

暂无评论

Can Automated Metadata Extraction Make Scientific Data More ...

IEEE International Conference on e-science and Grid Computing

作者： Tyler J. Skluzacek Kyle Chard Ian Foster Oak Ridge National Lab National Center for Computational Sciences Oak Ridge TN Department of Computer Science University of Chicago Chicago IL Data Science and Learning Division Argonne National Lab Lemont IL

FAIR principles require that scientific data be findable, discoverable, and reusable by users. To enable FAIRness, practioners of a science repository will often construct a rich, searchable index of metadata derived from the data. Unfortunately, manual metadata annotation methods do not scale to the many data files generated by many projects; and instead automated extraction systems are needed to scalably parse these files—often with nonstandard schema requiring specialized parsing strategies—and deposit representative metadata into a search index. In this work, we evaluate whether, and the extent to which, automatically extracted metadata make research repositories more navigable. We present a two-part user study conducted with scientists at two U.S. national laboratories from projects spanning spectroscopy and battery modeling. We constructed research indexes automatically by using the Xtract metadata extraction system. In the first part of our study, we learned about each user's role and identified key navigation concerns for scientists. We found that participants wished to navigate for purposes of discovery, retrieval, and organization. In the second part, participants completed simulated research data navigation tasks crafted to reflect real-world navigability concerns. We found that regardless of the interface used, participants consistently solved navigation tasks with high degrees of confidence and correctness, and significantly ( $1.2\mathrm{X}-50\times$ ) faster than via their alternative methods (e.g., manual directory scans or designing a customized navigational tool).

关键词：