检索结果-内蒙古大学图书馆

Numerical Stability of DeepGOPlus Inference

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Pepe, Inés Gonzalez Chatelain, Yohan Kiar, Gregory Glatard, Tristan Department of Computer Science and Software Engineering Concordia University Montreal Canada Center for the Developing Brain Child Mind Institute New YorkNY United States

Convolutional neural networks (CNNs) are currently among the most widely-used deep neural network (DNN) architectures available and achieve state-of-the-art performance for many problems. Originally applied to computer vision tasks, CNNs work well with any data with a spatial relationship, besides images, and have been applied to different fields. However, recent works have highlighted numerical stability challenges in DNNs, which also relates to their known sensitivity to noise injection. These challenges can jeopardise their performance and reliability. This paper investigates DeepGOPlus, a CNN that predicts protein function. DeepGOPlus has achieved state-of-the-art performance and can successfully take advantage and annotate the abounding protein sequences emerging in proteomics. We determine the numerical stability of the model's inference stage by quantifying the numerical uncertainty resulting from perturbations of the underlying floating-point data. In addition, we explore the opportunity to use reduced-precision floating point formats for DeepGOPlus inference, to reduce memory consumption and latency. This is achieved by instrumenting DeepGOPlus' execution using Monte Carlo Arithmetic, a technique that experimentally quantifies floating point operation errors and VPREC, a tool that emulates results with customizable floating point precision formats. Focus is placed on the inference stage as it is the primary deliverable of the DeepGOPlus model, widely applicable across different environments. All in all, our results show that although the DeepGOPlus CNN is very stable numerically, it can only be selectively implemented with lower-precision floating-point formats. We conclude that predictions obtained from the pre-trained DeepGOPlus model are very reliable numerically, and use existing floating-point formats efficiently. © 2022, CC BY.

关键词： Proteins

pFedLVM: A Large Vision Model (LVM)-Driven and Latent Feature-Based Personalized Federated Learning Framework in Autonomous Driving

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Kou, Wei-Bin Lin, Qingfeng Tang, Ming Xu, Sheng Ye, Rongguang Leng, Yang Wang, Shuai Li, Guofa Chen, Zhenyu Zhu, Guangxu Wu, Yik-Chung Department of Electrical and Electronic Engineering The University of Hong Kong Hong Kong Shenzhen Research Institute of Big Data Shenzhen China Department of Computer Science and Engineering Southern University of Science and Technology Shenzhen China Research Institute of Electronic Science and Technology University of Electronic Science and technology Chengdu China Shenzhen Institute of Advanced Technology Chinese Academy of Sciences Shenzhen China State Key Laboratory for Novel Software Technology Nanjing University Nanjing China College of Mechanical and Vehicle Engineering Chongqing University Chongqing China

Deep learning-based Autonomous Driving (AD) semantic segmentation (SSeg) models often exhibit poor generalization due to data heterogeneity in an ever domain-shifting environment. While Federated Learning (FL) could improve the generalization of an AD SSeg model (known as FedAD system), conventional models often struggle with under-fitting as the amount of accumulated training data progressively increases. To address this issue, instead of conventional small models, employing Large Vision Models (LVMs) in FedAD is a viable option for better learning of representations from a vast volume of data. However, implementing LVMs in FedAD introduces three challenges: (I) the extremely high communication overheads associated with transmitting LVMs between participating vehicles and a central server;(II) lack of computing resource to deploy LVMs on each vehicle;(III) the performance drop due to LVM focusing on shared features but overlooking local vehicle characteristics. To overcome these challenges, we propose pFedLVM, a LVM-Driven, Latent Feature-Based Personalized Federated Learning framework. In this approach, the LVM is deployed only on central server, which effectively alleviates the computational burden on individual vehicles. Furthermore, the exchange between central server and vehicles are the learned features rather than the LVM parameters, which significantly reduces communication overhead. In addition, we utilize both shared features from all participating vehicles and individual characteristics from each vehicle to establish a personalized learning mechanism. This enables each vehicle’s model to learn features from others while preserving its personalized characteristics, thereby outperforming globally shared models trained in general FL. Extensive experiments demonstrate that pFedLVM outperforms the existing state-of-the-art approach by 18.47%, 25.60%, 51.03% and 14.19% in terms of mIoU, mF1, mPrecision and mRecall, respectively. © 2024, CC BY-NC-ND.

关键词： Semantic Segmentation

AutoDebloater: Automated Android App Debloating

学校读者我要写书评

暂无评论

AutoDebloater: Automated Android App Debloating

IEEE International Conference on Automated software engineering (ASE)

作者： Jiakun Liu Xing Hu Ferdian Thung Shahar Maoz Eran Toch Debin Gao David Lo School of Computing and Information Systems Singapore Management University Singapore School of Software Technology Zhejiang University China School of Computer Science Tel Aviv University Israel Department of Industrial Engineering Tel Aviv University Israel

Android applications are getting bigger with an increasing number of features. However, not all the features are needed by a specific user. The unnecessary features can increase the attack surface and cost additional resources (e.g., storage and memory). Therefore, it is important to remove unnecessary features from Android applications. However, it is difficult for the end users to fully explore the apps to identify the unnecessary features, and there is no off-the-shelf tool available to assist users to debloat the apps by themselves. In this work, we propose AutoDebloater to debloat Android applications automatically for end users. AutoDebloater is a web application that can be accessed by end-users through a web browser. In particular, AutoDebloater can automatically explore an app and identify the transitions between activities. Then, AutoDebloater will present the Activity Transition Graph to users and ask them to select the activities they do not want to keep. Finally, AutoDebloater will remove the activities that are selected by users from the app. We conducted a user study on five Android apps downloaded from three categories (i.e., Finance, Tools, and Navigation) in Google Play and F-Droid. The results show that users are satisfied with AutoDebloater in terms of the stability of the debloated apps and the ability of AutoDebloater to identify features that are never noticed before. The tool is available at http://***. The code is available at https://***/jiakun-liu/autodebloater/ and the demonstration video can be found at https://***/Gmz0-p2n9D4.

关键词：

VAE Latent Space Quantization Methods for UAVs Video Stream

学校读者我要写书评

暂无评论

VAE Latent Space Quantization Methods for UAVs Video Stream

Information, Control, and Communication Technologies (ICCT), International Conference on

作者： Alexander Chenskiy Alexander Berezkin Roman Vivchar Ruslan Kirichek Dmitry Kukunin Advanced Projects and Developments Department Bonch-Bruevich Saint-Petersburg University of Telecommunications Saint-Petersburg Russia Software Engineering and Computer Science Department Bonch-Bruevich Saint-Petersburg University of Telecommunications Saint-Petersburg Russia Communication Networks and Data Transmission Department Bonch-Bruevich Saint-Petersburg University of Telecommunications Saint-Petersburg Russia

ISBN: (数字)9798331517564

ISBN: (纸本)9798331517571

In FPV control of unmanned aerial vehicles, video frames are transmitted to the external pilot's station via a down link. Down links utilize mobile and hybrid orbital-terrestrial communication networks. The efficiency increase in their utilization is achieved by reducing the required bandwidth for each FPV-controlled unmanned aircraft. This requires ensuring a high compression rate of video stream frames, for which methods based on the application of variational autoencoders can be used. The principle of their operation is as follows: encoding frames into latent space, quantization and lossless compression. This paper presents new quantization algorithms and investigates the effect of applying different quantization algorithms to compression rate of latent space of VQ-D6 variational autoencoder from Stable Diffusion during further lossless compression using LZMA algorithm. In the result, the most effective quantization is selected to be used together with lossless compression.

关键词： Space vehicles Quantization (signal) Image coding Tensors Autoencoders Neural networks Bandwidth Streaming media Autonomous aerial vehicles Orbits

An Empathetic AI Coach for Self-Attachment Therapy

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Alazraki, Lisa Ghachem, Ali Polydorou, Neophytos Khosmood, Foaad Edalat, Abbas Department of Computing Imperial College London United Kingdom Computer Science and Software Engineering California Polytechnic State University San Luis Obispo United States

In this work, we present a new dataset and a computational strategy for a digital coach that aims to guide users in practicing the protocols of self-attachment therapy. Our framework augments a rule-based conversational agent with a deep-learning classifier for identifying the underlying emotion in a user’s text response, as well as a deep-learning assisted retrieval method for producing novel, fluent and empathetic utterances. We also craft a set of human-like personas that users can choose to interact with. Our goal is to achieve a high level of engagement during virtual therapy sessions. We evaluate the effectiveness of our framework in a non-clinical trial with N=16 participants, all of whom have had at least four interactions with the agent over the course of five days. We find that our platform is consistently rated higher for empathy, user engagement and usefulness than the simple rule-based framework. Finally, we provide guidelines to further improve the design and performance of the application, in accordance with the feedback received. Copyright © 2022, The Authors. All rights reserved.

关键词： Deep learning

Energy-efficient UAV multicasting with simultaneous FSO backhaul and power transfer

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Che, Yue Ling Long, Weibin Luo, Sheng Wu, Kaishun Zhang, Rui The College of Computer Science and Software Engineering Shenzhen University China The Department of Electrical and Computer Engineering National University of Singapore Singapore

This letter studies an unmanned aerial vehicle (UAV) aided multicasting (MC) system, which is enabled by simultaneous free space optics (FSO) backhaul and power transfer. The UAV applies the power-splitting technique to harvest wireless power and decode backhaul information simultaneously over the FSO link, while at the same time using the harvested power to multicast the backhauled information over the radio frequency (RF) links to multiple ground users (GUs). We derive the UAV's achievable MC rate under the Poisson point process (PPP) based GU distribution. By jointly designing the FSO and RF links and the UAV altitude, we maximize the system-level energy efficiency (EE), which can be equivalently expressed as the ratio of the UAV's MC rate over the optics base station (OBS) transmit power, subject to the UAV's sustainable operation and reliable backhauling constraints. Due to the non-convexity of this problem, we propose suboptimal solutions with low complexity. Numerical results show the close-to-optimal EE performance by properly balancing the power-rate tradeoff between the FSO power and the MC data transmissions. Copyright © 2021, The Authors. All rights reserved.

关键词： Energy transfer

Generalizing Few Data to Unseen Domains Flexibly Based on Label Smoothing Integrated with Distributionally Robust Optimization

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Wang, Yangdi Zhang, Zhi-Hai Xu, Su Xiu Guo, Wenming School of Management Beijing Institute of Technology Beijing100081 China Department of Industrial Engineering Tsinghua University Beijing100084 China School of Management Beijing Institute of Technology Beijing100081 China School of Computer Science National Pilot Software Engineering School Beijing University of Posts and Telecommunications Beijing100876 China

Overfitting commonly occurs when applying deep neural networks (DNNs) on small-scale datasets, where DNNs do not generalize well from existing data to unseen data. The main reason resulting in overfitting is that small-scale datasets cannot reflect the situations of the real world. Label smoothing (LS) is an effective regularization method to prevent overfitting, avoiding it by mixing one-hot labels with uniform label vectors. However, LS only focuses on labels while ignoring the distribution of existing data. In this paper, we introduce the distributionally robust optimization (DRO) to LS, achieving shift the existing data distribution flexibly to unseen domains when training DNNs. Specifically, we prove that the regularization of LS can be extended to a regularization term for the DNNs parameters when integrating DRO. The regularization term can be utilized to shift existing data to unseen domains and generate new data. Furthermore, we propose an approximate gradient-iteration label smoothing algorithm (GI-LS) to achieve the findings and train DNNs. We prove that the shift for the existing data does not influence the convergence of GI-LS. Since GI-LS incorporates a series of hyperparameters, we further consider using Bayesian optimization (BO) to find the relatively optimal combinations of these hyperparameters. Taking small-scale anomaly classification tasks as a case, we evaluate GI-LS, and the results clearly demonstrate its superior performance. Copyright © 2024, The Authors. All rights reserved.

关键词： Deep neural networks

PIDray: A Large-scale X-ray Benchmark for Real-World Prohibited Item Detection

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Zhang, Libo Jiang, Lutao Ji, Ruyi Fan, Heng Institute of Software Chinese Academy of Sciences China University of Chinese Academy of Sciences China Department of Computer Science and Engineering University of North Texas United States

Automatic security inspection relying on computer vision technology is a challenging task in real-world scenarios due to many factors, such as intra-class variance, class imbalance, and occlusion. Most previous methods rarely touch the cases where the prohibited items are deliberately hidden in messy objects because of the scarcity of large-scale datasets, hindering their applications. To address this issue and facilitate related research, we present a large-scale dataset, named PIDray, which covers various cases in real-world scenarios for prohibited item detection, especially for deliberately hidden items. In specific, PIDray collects 124, 486 X-ray images for 12 categories of prohibited items, and each image is manually annotated with careful inspection, which makes it, to our best knowledge, to largest prohibited items detection dataset to date. Meanwhile, we propose a general divide-and-conquer pipeline to develop baseline algorithms on PIDray. Specifically, we adopt the tree-like structure to suppress the influence of the long-tailed issue in the PIDray dataset, where the first course-grained node is tasked with the binary classification to alleviate the influence of head category, while the subsequent fine-grained node is dedicated to the specific tasks of the tail categories. Based on this simple yet effective scheme, we offer strong task-specific baselines across object detection, instance segmentation, and multi-label classification tasks and verify the generalization ability on common datasets (e.g., COCO and PASCAL VOC). Extensive experiments on PIDray demonstrate that the proposed method performs favorably against current state-of-the-art methods, especially for deliberately hidden items. Our benchmark and codes will be released at https://***/lutao2021/PIDray. Copyright © 2022, The Authors. All rights reserved.

关键词： Object detection

DFU_MultiNet: A deep neural network approach for detecting diabetic foot ulcers through multi-scale feature fusion using the DFU dataset

学校读者我要写书评

暂无评论

Intelligence-Based Medicine 2023年 8卷 100128-100128页

作者： Biswas, Shuvo Mostafiz, Rafid Paul, Bikash Kumar Mohi Uddin, Khandaker Mohammad Rahman, Md Masudur Shariful, F.N.U. Department of Information and Communication Technology Mawlana Bhashani Science and Technology University Bangladesh Institute of Information Technology Noakhali Science and Technology University Bangladesh Department of Software Engineering Daffodil International University Bangladesh Department of Computer Science and Engineering Dhaka International University Bangladesh Department of Information and Communications Engineering Noakhali Science and Technology University Bangladesh School of Computing University of North Florida Jacksonville FL United States

Diabetic foot ulcer (DFU) is a common problem among people with diabetes that can result in amputation of the affected limb. Modern DFU treatment and diagnosis methods are expensive and time-consuming. Today, the development of the computer-aided diagnosis (CAD) method makes it possible for pathologists to diagnose DFU more swiftly and accurately. This has led to a rise in interest in deep learning (DL) approaches based on CAD. In this study, we introduce a novel framework called “DFU_MultiNet,” which focuses on the transfer learning approach to classify healthy and ulcer skin images using publicly available repositories. The proposed framework is developed to offer an efficient and robust method for DFU classification that determines the distinction between healthy and ulcerated skin. The proposed approach extracts features from foot samples using three well-known pre-trained CNN models: VGG19, DenseNet201, and NasNetMobile. Finally, these extracted results are merged through a summing layer to create a powerful hybrid network. Through obtaining impressive accuracy (99.06 %), precision (100.00 %), recall (98.18 %), specificity (100.00 %), F1-score (99.08 %), and AUC (99.09 %) the proposed “DFU_MultiNet” framework holds great potential as a diagnostic tool in healthcare and clinical settings. © 2023 The Author(s)

关键词： computer aided diagnosis (CAD) DenseNet201 Diabetic foot ulcer (DFU) Feature fusion NasNetMobile VGG19