检索结果-内蒙古大学图书馆

arXiv 2024年

作者： Chen, Xiangyu Yang, Fan Wang, Chen Lab Institute for Artificial Intelligence and Data Science Department of Computer Science and Engineering University at Buffalo NY14260 United States Robotic Systems Lab ETH Zürich Zürich8092 Switzerland

The pathfinding problem, which aims to identify a collision-free path between two points, is crucial for many applications, such as robot navigation and autonomous driving. Classic methods, such as A∗ search, perform well on small-scale maps but face difficulties scaling up. Conversely, data-driven approaches can improve pathfinding efficiency but require extensive data labeling and lack theoretical guarantees, making it challenging for practical applications. To combine the strengths of the two methods, we utilize the imperative learning (IL) strategy and propose a novel self-supervised pathfinding framework, termed imperative learning-based A∗ (iA∗). Specifically, iA∗ is a bilevel optimization process where the lower-level optimization is dedicated to finding the optimal path by a differentiable A∗ search module, and the upper-level optimization narrows down the search space to improve efficiency via setting suitable initial values from a data-driven model. Besides, the model within the upper-level optimization is a fully convolutional network, trained by the calculated loss in the lower-level optimization. Thus, the framework avoids extensive data labeling and can be applied in diverse environments. Our comprehensive experiments demonstrate that iA∗ surpasses both classical and data-driven methods in pathfinding efficiency and shows superior robustness among different tasks, validated with public datasets and simulation environments. Copyright © 2024, The Authors. All rights reserved.

关键词： Efficiency

来源：评论

学校读者我要写书评

暂无评论

Breaking Barriers in Physical-World Adversarial Examples: Improving Robustness and Transferability via Robust Feature

arXiv

引用

arXiv 2024年

作者： Wang, Yichen Chou, Yuxuan Zhou, Ziqi Zhang, Hangtao Wan, Wei Hu, Shengshan Li, Minghui National Engineering Research Center for Big Data Technology and System China Services Computing Technology and System Lab China Cluster and Grid Computing Lab China Hubei Engineering Research Center on Big Data Security China Hubei Key Laboratory of Distributed System Security China School of Cyber Science and Engineering Huazhong University of Science and Technology China School of Computer Science and Technology Huazhong University of Science and Technology China School of School of Software Engineering Huazhong University of Science and Technology China

As deep neural networks (DNNs) are widely applied in the physical world, many researches are focusing on physical-world adversarial examples (PAEs), which introduce perturbations to inputs and cause the model’s incorrect outputs. However, existing PAEs face two challenges: unsatisfactory attack performance (i.e., poor transferability and insufficient robustness to environment conditions), and difficulty in balancing attack effectiveness with stealthiness, where better attack effectiveness often makes PAEs more perceptible. In this paper, we explore a novel perturbation-based method to overcome the challenges. For the first challenge, we introduce a strategy Deceptive RF injection based on robust features (RFs) that are predictive, robust to perturbations, and consistent across different models. Specifically, it improves the transferability and robustness of PAEs by covering RFs of other classes onto the predictive features in clean images. For the second challenge, we introduce another strategy Adversarial Semantic Pattern Minimization, which removes most perturbations and retains only essential adversarial patterns in AEs. Based on the two strategies, we design our method Robust Feature Coverage Attack (RFCoA), comprising Robust Feature Disentanglement and Adversarial Feature Fusion. In the first stage, we extract target class RFs in feature space. In the second stage, we use attention-based feature fusion to overlay these RFs onto predictive features of clean images and remove unnecessary perturbations. Experiments show our method’s superior transferability, robustness, and stealthiness compared to existing state-of-the-art methods. Additionally, our method’s effectiveness can extend to Large Vision-Language Models (LVLMs), indicating its potential applicability to more complex tasks. Copyright © 2024, The Authors. All rights reserved.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

Color-Based Ripeness Classification of Oil Palm Fresh Fruit Bunches Using Convolution Neural Networks and data Augmentation

Color-Based Ripeness Classification of Oil Palm Fresh Fruit ...

引用

IEEE International Conference on Electronics and Communication engineering (ICECE)

作者： Juhaida Abu Bakar Mahmoud A M Kehail Muhamad Syafiq Mat Kassim Ranjithkumar Saravanan Zhao Wei Cheng Ali Ghazi Dahham Al-Marsoomi Data Science Research Lab School of Computing Universiti Utara Malaysia Kedah Malaysia Department of Mechanical Engineering UCSI University Cheras Malaysia

ISBN: (数字)9798331517755

ISBN: (纸本)9798331517762

Proper ripeness categorization of oil palm fresh fruit bunches is essential to ensure they are harvested at the optimal stage to maximize oil output. The current manual method of ripeness assessment, which relies on harvesters visually inspecting the fruit's color, is both labor-intensive and prone to human error. To address these limitations, there is a growing need for an automated classification system that leverages artificial intelligence. The manual classification process is cumbersome and susceptible to inaccuracies due to its reliance on subjective visual inspection. This labor-intensive approach increases the likelihood of human error, underscoring the necessity for a more reliable and efficient automated solution. Thus, this study aims to evaluate the feasibility of using Convolutional Neural Networks for automating the grading based on color. A dataset was compiled from various sources and augmented using a data generator. The model was constructed incorporating a transfer learning approach with an Xception model. The model achieved an overall accuracy of 80.4%. Visualization of the model using activation maps confirmed that the model can effectively classify the color, indicating its potential viability for the task.

关键词： Analytical models Accuracy Image color analysis Oils Computational modeling Transfer learning data visualization Manuals data models Graphical user interfaces

来源：评论

学校读者我要写书评

暂无评论

PROTOTYPE-BASED OPTIMAL TRANSPORT FOR OUT-OF-DISTRIBUTION DETECTION

arXiv

引用

arXiv 2024年

作者： Ke, Ao Chen, Wenlong Feng, Chuanwen Cao, Yukun Xie, Xike Kevin Zhou, S. Feng, Lei School of Biomedical Engineering University of Science and Technology China Data Darkness Lab MIRACLE Center Suzhou Institute for Advanced Research USTC China

Detecting Out-of-Distribution (OOD) inputs is crucial for improving the reliability of deep neural networks in the real-world deployment. In this paper, inspired by the inherent distribution shift between ID and OOD data, we propose a novel method that leverages optimal transport to measure the distribution discrepancy between test inputs and ID prototypes. The resulting transport costs are used to quantify the individual contribution of each test input to the overall discrepancy, serving as a desirable measure for OOD detection. To address the issue that solely relying on the transport costs to ID prototypes is inadequate for identifying OOD inputs closer to ID data, we generate virtual outliers to approximate the OOD region via linear extrapolation. By combining the transport costs to ID prototypes with the costs to virtual outliers, the detection of OOD data near ID data is emphasized, thereby enhancing the distinction between ID and OOD inputs. Experiments demonstrate the superiority of our method over state-of-the-art methods. © 2024, CC BY.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

Enabling Complete Atomicity for Cross-Chain Applications Through Layered State Commitments

Enabling Complete Atomicity for Cross-Chain Applications Thr...

引用

Reliable Distributed Systems

作者： Yuandi Cai Ru Cheng Yifan Zhou Shijie Zhang Jiang Xiao Hai Jin Services Computing Technology and System Lab Cluster and Grid Computing Lab National Engineering Research Center for Big Data Technology and System School of Computer Science and Technology Huazhong University of Science and Technology China

ISBN: (数字)9798331530037

ISBN: (纸本)9798331530044

Cross-chain Decentralized Applications (dApps) are increasingly popular for their ability to handle complex tasks across various blockchains, extending beyond simple asset transfers or swaps. However, ensuring all dependent transactions execute correctly together, known as complete atomicity, remains a challenge. Existing works provide financial atomicity, protecting against monetary loss, but lack the ability to ensure correctness for complex tasks. In this paper, we introduce Avalon, a transaction execution framework for cross-chain dApps that guarantees complete atomicity for the first time. Avalon achieves this by introducing multiple state layers above the native one to cache state transitions, allowing for efficient management of these state transitions. Most notably, for concurrent cross-chain transactions, Avalon resolves not only intra-chain conflicts but also addresses potential inconsistencies between blockchains via a novel state synchronization protocol, enabling serializable cross-chain execution. We implement Avalon using smart contracts in Cosmos ecosystem and evaluate its commitment performance, demonstrating acceptable latency and gas consumption even under conflict cases.

关键词： Atomic layer deposition Smart contracts Ecosystems Decentralized applications Consensus protocol Synchronization Reliability Interoperability

来源：评论

学校读者我要写书评

暂无评论

MMCNet: deep learning–based multimodal classification model using dynamic knowledge

引用

Personal and Ubiquitous Computing 2022年第2期26卷 355-364页

作者： Park, Sung-Soo Chung, Kyungyong Data Mining Lab. Department of Computer Science Kyonggi University 154-42 Gwanggyosan-ro Yeongtong-gu Gyeonggi-do Suwon-si16227 Korea Republic of Division of Computer Science and Engineering Kyonggi University 154-42 Gwanggyosan-ro Yeongtong-gu Gyeonggi-do Suwon-si16227 Korea Republic of

Because of the growth of the business sector dealing in the distribution of movies, software, music, and other contents, a very large amount of contents has accumulated. Accordingly, recommendation systems for inducing user requests for contents are more important. In distribution businesses, accurate content recommendations are required to secure and retain users. To establish a highly accurate recommendation system, the recommended contents must be accurately classified. As classification methods, mainly techniques such as naive Bayes, SGD (stochastic gradient descent), and SVM (support vector machine), are utilized. If all of the information on recommended subjects is applied in the classification process, high-level accuracy can be expected, but heavy calculation, a long service time, and low scalability are incurred. Given this inefficiency, effective classification in which the metadata of contents are used is required. Metadata are expressed in the forms of the domain concept, relation, type, and attribute to allow the complicated relations between multimodal data (text, images, and video) to be processed efficiently. Most classification systems use single modal data to express one piece of knowledge for an item in a domain. Single modal data are limited in terms of improving classification accuracy, because they do not include the useful information provided by different knowledge types. Therefore, in this paper, we propose MMCNet, a deep learning–based multimodal classification model that uses dynamic knowledge. The proposed method consists of a classification model that applies the human learning principle-based CNN (convolution neural network) to multimodal data in combination with text and image knowledge. By using a Web robot agent, multimodal data are collected from the TMDb (The Movie database) data set, which includes a variety of single modal data. In the preprocessing procedures, knowledge integration, knowledge conversion, and knowledge reduction

关键词： Classification (of information)

来源：评论

学校读者我要写书评

暂无评论

NC-ALG: Graph-Based Active Learning under Noisy Crowd 40

NC-ALG: Graph-Based Active Learning under Noisy Crowd

引用

40th IEEE International Conference on data engineering, ICDE 2024

作者： Zhang, Wentao Wang, Yexin You, Zhenbang Li, Yang Cao, Gang Yang, Zhi Cui, Bin Center for Machine Learning Research Peking University China Key Lab of High Confidence Software Technologies Peking University China Institute of Advanced Algorithms Research Shanghai China Institute of Computational Social Science Peking University Qingdao China National Engineering Labratory for Big Data Analytics and Applications China TEG Tencent Inc. Department of Data Platform China Beijing Academy of Artificial Intelligence China

ISBN: (纸本)9798350317152

Graph Neural Networks (GNNs) have achieved great success in various data mining tasks but they heavily rely on a large number of annotated nodes, requiring considerable human efforts. Despite the effectiveness of existing GNN-based Active Learning (AL) methods, they assume that the annotated labels are always correct, which is contradictory to the error-prone labeling process in a practical crowdsourcing environment. Besides, due to this impractical assumption, existing works only focus on optimizing the node selection in AL but neglect optimizing the labeling process. Therefore, we present NC-ALG, the first GNN-based AL framework that optimizes both the node selection and node labeling process under a noisy crowd. For node selection, NC-ALG introduces a new measurement to model influence reliability and an effective influence maximization objective to select nodes. For node labeling, NC-ALG significantly reduces the labeling cost by considering the model-predicted labels and the labels of mirror nodes. To the best of our knowledge, this is the first attempt to consider GNN-based AL under the practical noisy crowd. Empirical studies on public datasets demonstrate that NC-ALG significantly outperforms existing methods in terms labeling efficiency. Notably, it only takes NC-ALG one-third of the labeling budget that the competitive baseline GRAIN needs to achieve an accuracy of 70.7 % on PubMed. © 2024 IEEE.

关键词： Crowdsourcing

来源：评论

学校读者我要写书评

暂无评论

A Transformer-Based Spatio-Temporal Graph Neural Network for Anomaly Detection on Dynamic Graphs 12th

A Transformer-Based Spatio-Temporal Graph Neural Network for...

引用

12th CCF Conference on Bigdata, Bigdata 2024

作者： Gao, Yuanjun Zhu, Quntao Shi, Xuanhua Jin, Hai National Engineering Research Center for Big Data Technology and System Services Computing Technology and System Lab Cluster and Grid Computing Lab School of Computer Science and Technology Huazhong University of Science and Technology Wuhan430074 China

ISBN: (纸本)9789819610235

Dynamic graphs have emerged as a pivotal data structure underpinning real-world network applications. Against this backdrop, detecting anomalies in dynamic graphs has become particularly important, serving as a foundation for multiple downstream tasks. However, existing research has been limited by only considering the simplistic spatial features of the target edge and being confined to local spatial structures. This confinement imposes significant limitations on model performance. Furthermore, current models have not adequately addressed the issue of missing node attributes, relying solely on one-hot encoding to represent nodes, which restricts the expressive capacity of spatial features. In response to these challenges, we propose an end-to-end transformer-based spatio-temporal graph neural network model called TransSTGNN for detecting anomalous edges on dynamic graphs. This model innovatively integrates the graph convolution network with the transformer model to extract multi-dimensional spatial features of the target edge. Simultaneously, TransSTGNN incorporates a novel node enhancement module that reinforces the representation capability of spatial features by encoding the spatial attributes of nodes, effectively tackling the problem of missing node attributes. Extensive experiments confirm that TransSTGNN surpasses the state-of-the-art methods in anomaly detection on six benchmark datasets and effectively resolves the challenges mentioned above. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Spatio-temporal data

来源：评论

学校读者我要写书评

暂无评论

Stealthy Backdoor Attack Towards Federated Automatic Speaker Verification

Stealthy Backdoor Attack Towards Federated Automatic Speaker...

引用

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

作者： Longling Zhang Lyqi Liu Dan Meng Jun Wang Shengshan Hu School of Cyber Science and Engineering Huazhong University of Science and Technology China National Engineering Research Center for Big Data Technology and System Services Computing Technology and System Lab Hubei Key Laboratory of Distributed System Security Hubei Engineering Research Center on Big Data Security OPPO Research Institute China

Automatic speech verification (ASV) authenticates individuals based on distinct vocal patterns, playing a pivotal role in many applications such as voice-based unlocking systems for devices. The ASV system comprises three stages: training, registration, and validation. The model refines using voice data in training, extracts vocal features in registration, and contrasts these with speech patterns in validation. Modern ASV models, primarily grounded in DNN architectures, require extensive data for training. Federated learning (FL) fosters model-sharing across multiple clients while ensuring data privacy. Due to its open architecture, FL is vulnerable to backdoor attacks. However, training a stealthy backdoor attack in FL presents challenges, including diminished attack generalization owing to data heterogeneity, and conspicuous triggers that render them easily detectable. In this paper, we propose a Federated Stealthy Backdoor Attack method ($FedSBA$). FedSBA aims to improve the attack model’s generalization, enhance its persistence, and elude anomaly detection under the heterogeneous data distribution. FedSBA constructs an attack model based on a personalized transformer and encompasses a stealthy trigger. Moreover, we also propose a defensive strategy that utilizes an adaptive weight aggregation scheme. The stealthiness and effectiveness of FedSBA are demonstrated by exhibiting superior performance in comparison to previous works.

关键词：

来源：评论

学校读者我要写书评

暂无评论

PSMiner: A Pattern-Aware Accelerator for High-Performance Streaming Graph Pattern Mining 23

PSMiner: A Pattern-Aware Accelerator for High-Performance St...

引用

Proceedings of the 60th Annual ACM/IEEE Design Automation Conference

作者： Hao Qi Yu Zhang Ligang He Kang Luo Jun Huang Haoyu Lu Jin Zhao Hai Jin National Engineering Research Center for Big Data Technology and System Services Computing Technology and System Lab Cluster and Grid Computing Lab School of Computer Science and Technology Huazhong University of Science and Technology China National Engineering Research Center for Big Data Technology and System Services Computing Technology and System Lab Cluster and Grid Computing Lab School of Computer Science and Technology Huazhong University of Science and Technology China and Zhejiang-HUST Joint Research Center for Graph Processing Zhejiang Lab China Department of Computer Science University of Warwick United Kingdom

ISBN: (纸本)9798350323481

Streaming Graph Pattern Mining (GPM) has been widely used in many application fields. However, the existing streaming GPM solution suffers from many unnecessary explorations and isomorphism tests, while the existing static GPM ones require many repetitive operations to compute the full graph. In this paper, we propose a pattern-aware incremental execution approach and design the first streaming GPM accelerator called PSMiner, which integrates multiple optimizations to reduce redundant computation and improve computing efficiency. We have conducted extensive experiments. The results show that compared with the state-of-the-art software and hardware solutions, PSMiner achieves the average speedups of 770.9× and 60.4×, respectively.

关键词：

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：