检索结果-内蒙古大学图书馆

Training Artificial Neural Networks by Coordinate Search Algorithm

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Rokhsatyazdi, Ehsan Rahnamayan, Shahryar Miyandoab, Sevil Zanjani Bidgoli, Azam Asilian Tizhoosh, H.R. Lab Department of Electrical Computer and Software Engineering Ontario Tech University OshawaON Canada Department of Engineering Brock University St. CatharinesON Canada Faculty of Science Wilfrid Laurier University WaterlooON Canada Rhazes Lab Department of Artificial Intelligence and Informatics Mayo Clinic RochesterMN United States

Training Artificial Neural Networks (ANNs) poses a challenging and critical problem in machine learning. Despite the effectiveness of gradient-based learning methods, such as Stochastic Gradient Descent (SGD), in training neural networks, they do have several limitations. For instance, they require differentiable activation functions, and cannot optimize a model based on several independent non-differentiable loss functions simultaneously;for example, the F1-score, which is used during testing, can be used during training when a gradient-free optimization algorithm is utilized. Furthermore, the training (i.e., optimization of weights) in any DNN can be possible with a small size of the training dataset. To address these concerns, we propose an efficient version of the gradient-free Coordinate Search (CS) algorithm, an instance of General Pattern Search (GPS) methods, for training (i.e., optimizing) neural networks. The proposed algorithm can be used with non-differentiable activation functions and tailored to multi-objective/multi-loss problems. Finding the optimal values for weights of ANNs is a large-scale optimization problem. Therefore, instead of finding the optimal value for each variable, which is the common technique in classical CS, we accelerate optimization and convergence by bundling the variables (i.e., weights). In fact, this strategy is a form of dimension reduction for optimization problems. Based on the experimental results, the proposed method is comparable with the SGD algorithm, and in some cases, it outperforms the gradient-based approach. Particularly, in situations with insufficient labeled training data, the proposed CS method performs better. The performance plots demonstrate a high convergence rate, highlighting the capability of our suggested method to find a reasonable solution with fewer function calls. As of now, the only practical and efficient way of training ANNs with hundreds of thousands of weights is gradient-based algorithms such

关键词： Optimization

Ret3D: Rethinking Object Relations for Efficient 3D Object Detection in Driving Scenes

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Wu, Yu-Huan Zhang, Da Zhang, Le Zhan, Xin Dai, Dengxin Liu, Yun Cheng, Ming-Ming TMCC College of Computer Science Nankai University Tianjin China Alibaba DAMO Academy China University of Electronic Science and Technology of China China Max Planck Institute for Informatics Germany Computer Vision Lab ETH Zurich Switzerland

Current efficient LiDAR-based detection frameworks are lacking in exploiting object relations, which naturally present in both spatial and temporal manners. To this end, we introduce a simple, efficient, and effective two-stage detector, termed as Ret3D. At the core of Ret3D is the utilization of novel intra-frame and inter-frame relation modules to capture the spatial and temporal relations accordingly. More Specifically, intra-frame relation module (IntraRM) encapsulates the intra-frame objects into a sparse graph and thus allows us to refine the object features through efficient message passing. On the other hand, inter-frame relation module (InterRM) densely connects each object in its corresponding tracked sequences dynamically, and leverages such temporal information to further enhance its representations efficiently through a lightweight transformer network. We instantiate our novel designs of IntraRM and InterRM with general center-based or anchor-based detectors and evaluate them on Waymo Open Dataset (WOD). With negligible extra overhead, Ret3D achieves the state-of-the-art performance, being 5.5% and 3.2% higher than the recent competitor in terms of the LEVEL-1 and LEVEL-2 mAPH metrics on vehicle detection, respectively. © 2022, CC BY-NC-SA.

关键词： Object detection

MRI Parameter Mapping via Gaussian Mixture VAE: Breaking the Assumption of Independent Pixels

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Xu, Moucheng Zhou, Yukun Goodwin-Allcock, Tobias Firoozabadi, Kimia Jacob, Joseph Alexander, Daniel C. Slator, Paddy J. UCL Hawkes Institute United Kingdom UCL Satsuma Lab United Kingdom UCL Respiratory United Kingdom UCL Department of Computer Science United Kingdom UCL Medical School United Kingdom UCL Department of Medical Physics and Biomedical Engineering United Kingdom Cardiff University School of Computer Science and Informatics United Kingdom Cardiff University Brain Research Imaging Center United Kingdom

We introduce and demonstrate a new paradigm for quantitative parameter mapping in MRI. Parameter mapping techniques, such as diffusion MRI and quantitative MRI, have the potential to robustly and repeatably measure biologically-relevant tissue maps that strongly relate to underlying microstructure. Quantitative maps are calculated by fitting a model to multiple images, e.g. with least-squares or machine learning. However, the overwhelming majority of model fitting techniques assume that each voxel is independent, ignoring any co-dependencies in the data. This makes model fitting sensitive to voxelwise measurement noise, hampering reliability and repeatability. We propose a self-supervised deep variational approach that breaks the assumption of independent pixels, leveraging redundancies in the data to effectively perform data-driven regularisation of quantitative maps. We demonstrate that our approach outperforms current model fitting techniques in dMRI simulations and real data. Especially with a Gaussian mixture prior, our model enables sharper quantitative maps, revealing finer anatomical details that are not presented in the baselines. Our approach can hence support the clinical adoption of parameter mapping methods such as dMRI and qMRI. Our code is available at https://***/moucheng2017/MRI-GMM-VAE. © 2024, CC BY-NC-ND.

关键词： Mapping

MCCNet: Multi-Color Cascade Network with Weight Transfer for Single Image Depth Prediction on Outdoor Relief Images 25th

学校读者我要写书评

暂无评论

MCCNet: Multi-Color Cascade Network with Weight Transfer for...

25th International Conference on Pattern Recognition Workshops, ICPR 2020

作者： Frisky, Aufaclav Zatu Kusuma Putranto, Andi Zambanini, Sebastian Sablatnig, Robert Computer Vision Lab Institute of Visual Computing and Human-Centered Technology Faculty of Informatics TU Wien Vienna Austria Department of Computer Science and Electronics Faculty of Mathematics and Natural Sciences Universitas Gadjah Mada Yogyakarta Indonesia Department of Archaeology Faculty of Cultural Science Universitas Gadjah Mada Yogyakarta Indonesia

ISBN: (纸本)9783030687861

Single image depth prediction is considerably difficult since depth cannot be estimated from pixel correspondences. Thus, prior knowledge, such as registered pixel and depth information from the user is required. Another problem rises when targeting a specific domain requirement as the number of freely available training datasets is limited. Due to color problem in relief images, we present a new outdoor Registered Relief Depth (RRD) Prambanan dataset, consisting of outdoor images of Prambanan temple relief with registered depth information supervised by archaeologists and computer scientists. In order to solve the problem, we also propose a new depth predictor, called Multi-Color Cascade Network (MCCNet), with weight transfer. Applied on the new RRD Prambanan dataset, our method performs better in different materials than the baseline with 2.53 mm RMSE. In the NYU Depth V2 dataset, our method’s performance is better than the baselines and in line with other state-of-the-art works. © 2021, Springer Nature Switzerland AG.

关键词： Forecasting

The Lannion report on Big Data and Security Monitoring Research

学校读者我要写书评

暂无评论

The Lannion report on Big Data and Security Monitoring Resea...

2022 IEEE International Conference on Big Data, Big Data 2022

作者： D'Orazio, Laurent Boukhobza, Jalil Rana, Omer Agoun, Juba Gruenwald, Le Rannou, Herve Bertino, Elisa Hacid, Mohand-Said Saidi, Taofik Bossert, Georges Nguyen Huu, Van Long Tombroff, Dimitri Onizuka, Makoto Univ Rennes Cnrs Irisa B-Com Lannion France Ensta Bretagne Lab-STICC Cnrs Umr Brest6285 France Cardiff University School of Computer Science and Informatics Cardiff United Kingdom Université de Lyon Cnrs Liris Villeurbanne France University of Oklahoma School of Computer Science Norman United States SenX Guipavas France Purdue University West Department of Computer Science Lafayette United States Nokia Lannion France Sekoia Rennes France Nokia Bell Labs B-Com Lannion France Thales Service Thales Rennes France Osaka University Graduate School of Information Science and Technology Osaka Japan

ISBN: (纸本)9781665480451

During the last decade, big data management has attracted increasing interest from both the industrial and academic communities. In parallel, Cyber Security has become mandatory due to various and more intensive threats. In June 2022, a group of researchers has met to reflect on their community's impacts on current research challenges. In particular, they have considered four dimensions: (1) dedicated systems being data processing and analytic platforms or time series management systems;(2) graphs analytics and distributed computation;(3) privacy;and (4) new hardware. © 2022 IEEE.

关键词： Cybersecurity

Deep Gradient Learning for Efficient Camouflaged Object Detection

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Ji, Ge-Peng Fan, Deng-Ping Chou, Yu-Cheng Dai, Dengxin Liniger, Alexander Van Gool, Luc School of Computer Science Wuhan University Wuhan China Computer Vision Lab ETH Zürich Zürich Switzerland Vision for Autonomous Systems Group MPI for Informatics Saarbrücken Germany

This paper introduces DGNet, a novel deep framework that exploits object gradient supervision for camouflaged object detection (COD). It decouples the task into two connected branches, i.e., a context and a texture encoder. The essential connection is the gradient-induced transition, representing a soft grouping between context and texture features. Benefiting from the simple but efficient framework, DGNet outperforms existing state-of-the-art COD models by a large margin. Notably, our efficient version, DGNet-S, runs in real-time (80 fps) and achieves comparable results to the cutting-edge model JCSOD-CVPR21 with only 6.82% parameters. Application results also show that the proposed DGNet performs well in polyp segmentation, defect detection, and transparent object segmentation tasks. Codes will be made available at https://***/GewelsJI/DGNet. © 2022, CC BY.

关键词： Object detection

Disentangling Prosody Representations with Unsupervised Speech Reconstruction

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Qu, Leyuan Li, Taihao Weber, Cornelius Pekarek-Rosin, Theresa Ren, Fuji Wermter, Stefan The Institute of Artificial Intelligence Zhejiang Lab Hangzhou China The Department of Informatics University of Hamburg Hamburg Germany The School of Computer Science and Engineering University of Electronic Science and Technology of China Chengdu China

Human speech can be characterized by different components, including semantic content, speaker identity and prosodic information. Significant progress has been made in disentangling representations for semantic content and speaker identity in Automatic Speech Recognition (ASR) and speaker verification tasks respectively. However, it is still an open challenging research question to extract prosodic information because of the intrinsic association of different attributes, such as timbre and rhythm, and because of the need for supervised training schemes to achieve robust large-scale and speaker-independent ASR. The aim of this paper is to address the disentanglement of emotional prosody from speech based on unsupervised reconstruction. Specifically, we identify, design, implement and integrate three crucial components in our proposed speech reconstruction model Prosody2Vec: (1) a unit encoder that transforms speech signals into discrete units for semantic content, (2) a pretrained speaker verification model to generate speaker identity embeddings, and (3) a trainable prosody encoder to learn prosody representations. We first pretrain the Prosody2Vec representations on unlabelled emotional speech corpora, then fine-tune the model on specific datasets to perform Speech Emotion Recognition (SER) and Emotional Voice Conversion (EVC) tasks. Both objective (weighted and unweighted accuracies) and subjective (mean opinion score) evaluations on the EVC task suggest that Prosody2Vec effectively captures general prosodic features that can be smoothly transferred to other emotional speech. In addition, our SER experiments on the IEMOCAP dataset reveal that the prosody features learned by Prosody2Vec are complementary and beneficial for the performance of widely used speech pretraining models and surpass the state-of-the-art methods when combining Prosody2Vec with HuBERT representations. Some audio samples can be found on our demo website1 Copyright © 2022, The Authors. All righ

关键词： Speech recognition

HCA-NET: Hierarchical Context Attention Network for Intervertebral Disc Semantic labeling

学校读者我要写书评

暂无评论

HCA-NET: Hierarchical Context Attention Network for Interver...

IEEE International Symposium on Biomedical Imaging

作者： Afshin Bozorgpour Bobby Azad Reza Azad Yury Velichko Ulas Bagci Dorit Merhof Faculty of Informatics and Data Science University of Regensburg Germany Electrical Engineering and Computer Science Department South Dakota State University USA Faculty of Electrical Engineering and Information Technology RWTH Aachen University Germany Machine and Hybrid Intelligence Lab Northwestern University Chicago IL USA Fraunhofer Institute for Digital Medicine MEVIS Germany

ISBN: (数字)9798350313338

ISBN: (纸本)9798350313345

Accurate and automated segmentation of intervertebral discs (IVDs) in medical images is crucial for assessing spine-related disorders, such as osteoporosis, vertebral fractures, or IVD herniation. We present HCA-Net, a novel contextual attention network architecture for semantic labeling of IVDs, with a special focus on exploiting prior geometric information. Our approach excels at processing features across different scales and effectively consolidating them to capture the intricate spatial relationships within the spinal cord. To achieve this, HCA-Net models IVD labeling as a pose estimation problem, aiming to minimize the discrepancy between each predicted IVD location and its corresponding actual joint location. In addition, we introduce a skeletal loss term to reinforce the model’s geometric dependence on the spine. This loss function is designed to constrain the model’s predictions to a range that matches the general structure of the human vertebral skeleton. As a result, the network learns to reduce the occurrence of false predictions and adaptively improves the accuracy of IVD location estimation. Through extensive experimental evaluation on multi-center spine datasets, our approach consistently outperforms previous state-of-the-art methods on both MRI T1w and T2w modalities. The code-base is accessible to the public on GitHub.

关键词： Adaptation models Accuracy Spinal cord Semantics Pose estimation Predictive models Skeleton

A Dense Retrieval System and Evaluation Dataset for Scientific Computational Notebooks

学校读者我要写书评

暂无评论

A Dense Retrieval System and Evaluation Dataset for Scientif...

IEEE International Conference on e-science and Grid Computing

作者： Na Li Yangjun Zhang Zhiming Zhao Multiscale Networked System Informatics Institute University of Amsterdam Netherlands School of Electronic Engineering and Computer Science Queen Mary University of London United Kingdom LifeWatch ERIC Virtual Lab and Innovation Center (VLIC) Amsterdam Netherlands

The discovery and reutilization of scientific codes are crucial in many research activities. Computational notebooks have emerged as a particularly effective medium for sharing and reusing scientific codes. Nevertheless, effectively locating relevant computational notebooks is a significant challenge. First, computational notebooks encompass multi-modal data comprising unstructured text, source code, and other media, posing complexities in representing such data for retrieval purposes. Second, the absence of evaluation datasets for the computational notebook search task hampers fair performance assessments within the research community. Prior studies have either treated computational notebook search as a code-snippet search problem or focused solely on content-based approaches for searching computational notebooks. To address the aforementioned difficulties, we present DeCNR, tackling the information needs of researchers in seeking computational notebooks. Our approach leverages a fused sparse-dense retrieval model to represent computational notebooks effectively. Additionally, we construct an evaluation dataset including actual scientific queries, computational notebooks, and relevance judgments for fair and objective performance assessment. Experimental results demonstrate that the proposed method surpasses baseline approaches in terms of F1@5 and NDCG@5. The proposed system has been implemented as a web service shipped with REST APIs, allowing seamless integration with other applications and web services.

关键词：