检索结果-内蒙古大学图书馆

Label Anything: An Interpretable, High-Fidelity and Prompt-Free Annotator

学校读者我要写书评

暂无评论

arXiv 2025年

作者： Kou, Wei-Bin Zhu, Guangxu Ye, Rongguang Wang, Shuai Tang, Ming Wu, Yik-Chung Department of Electrical and Electronic Engineering The University of Hong Kong Hong Kong Department of Computer Science and Engineering Southern University of Science and Technology Shenzhen China Shenzhen International Center For Industrial And Applied Mathematics Shenzhen Research Institute of Big Data Shenzhen China Shenzhen Institute of Advanced Technology Chinese Academy of Sciences Shenzhen China

Learning-based street scene semantic understanding in autonomous driving (AD) has advanced significantly recently, but the performance of the AD model is heavily dependent on the quantity and quality of the annotated training data. However, traditional manual labeling involves high cost to annotate the vast amount of required data for training robust model. To mitigate this cost of manual labeling, we propose a Label Anything Model (denoted as LAM), serving as an interpretable, high-fidelity, and prompt-free data annotator. Specifically, we firstly incorporate a pretrained Vision Transformer (ViT) to extract the latent features. On top of ViT, we propose a semantic class adapter (SCA) and an optimization-oriented unrolling algorithm (OptOU), both with a quite small number of trainable parameters. SCA is proposed to fuse ViT-extracted features to consolidate the basis of the subsequent automatic annotation. OptOU consists of multiple cascading layers and each layer contains an optimization formulation to align its output with the ground truth as closely as possible, though which OptOU acts as being interpretable rather than learning-based blackbox nature. In addition, training SCA and OptOU requires only a single pre-annotated RGB seed image, owing to their small volume of learnable parameters. Extensive experiments clearly demonstrate that the proposed LAM can generate high-fidelity annotations (almost 100% in mIoU) for multiple real-world datasets (i.e., Camvid, Cityscapes, and Apolloscapes) and CARLA simulation dataset. © 2025, CC BY-NC-ND.

关键词： Adversarial machine learning

Generative AI-enabled Blockchain Networks: Fundamentals, Applications, and Case Study

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Nguyen, Cong T. Liu, Yinqiu Du, Hongyang Hoang, Dinh Thai Niyato, Dusit Nguyen, Diep N. Mao, Shiwen The Institute of Fundamental and Applied Sciences Duy Tan University Viet Nam The School of Computer Science and Engineering Nanyang Technological University Singapore The School of Electrical and Data Engineering University of Technology Sydney Australia The Department of Electrical and Computer Engineering Auburn University Auburn United States

Generative Artificial Intelligence (GAI) has recently emerged as a promising solution to address critical challenges of blockchain technology, including scalability, security, privacy, and interoperability. In this paper, we first introduce GAI techniques, outline their applications, and discuss existing solutions for integrating GAI into blockchains. Then, we discuss emerging solutions that demonstrate the effectiveness of GAI in addressing various challenges of blockchain, such as detecting unknown blockchain attacks and smart contract vulnerabilities, designing key secret sharing schemes, and enhancing privacy. Moreover, we present a case study to demonstrate that GAI, specifically the generative diffusion model, can be employed to optimize blockchain network performance metrics. Experimental results clearly show that, compared to a baseline traditional AI approach, the proposed generative diffusion model approach can converge faster, achieve higher rewards, and significantly improve the throughput and latency of the blockchain network. Additionally, we highlight future research directions for GAI in blockchain applications, including personalized GAI-enabled blockchains, GAI-blockchain synergy, and privacy and security considerations within blockchain ecosystems. © 2024, CC BY-NC-SA.

关键词： Blockchain

Empowering Large Language Models in Wireless Communication: A Novel dataset and Fine-Tuning Framework

学校读者我要写书评

暂无评论

arXiv 2025年

作者： Lin, Yushen Zhang, Ruichen Huang, Wenqi Wang, Kaidi Ding, Zhiguo So, Daniel K.C. Niyato, Dusit School of Electrical and Electronic Engineering The University of Manchester M13 9PL United Kingdom Department of Electrical and Electronic Engineering University of Manchester Manchester United Kingdom Department of Computer Science Khalifa University Abu Dhabi United Arab Emirates College of Computing and Data Science Nanyang Technological University Singapore

In this work, we develop a specialized dataset aimed at enhancing the evaluation and fine-tuning of large language models (LLMs) specifically for wireless communication applications. The dataset includes a diverse set of multi-hop questions, including true/false and multiple-choice types, spanning varying difficulty levels from easy to hard. By utilizing advanced language models for entity extraction and question generation, rigorous data curation processes are employed to maintain high quality and relevance. Additionally, we introduce a Pointwise V-Information (PVI) based fine-tuning method, providing a detailed theoretical analysis and justification for its use in quantifying the information content of training data with 2.24% and 1.31% performance boost for different models compared to baselines, respectively. To demonstrate the effectiveness of the fine-tuned models with the proposed methodologies on practical tasks, we also consider different tasks, including summarizing optimization problems from technical papers and solving the mathematical problems related to non-orthogonal multiple access (NOMA), which are generated by using the proposed multi-agent framework. Simulation results show significant performance gain in summarization tasks with 20.9% in the ROUGE-L metrics. We also study the scaling laws of fine-tuning LLMs and the challenges LLMs face in the field of wireless communications, offering insights into their adaptation to wireless communication tasks. This dataset and fine-tuning methodology aim to enhance the training and evaluation of LLMs, contributing to advancements in LLMs for wireless communication research and applications. Copyright © 2025, The Authors. All rights reserved.

关键词： Large datasets

Multi-fidelity residual neural processes for scalable surrogate modeling 24

学校读者我要写书评

暂无评论

Multi-fidelity residual neural processes for scalable surrog...

Proceedings of the 41st International Conference on Machine Learning

作者： Ruijia Niu Dongxia Wu Kai Kim Yi-An Ma Duncan Watson-Parris Rose Yu Department of Computer Science and Engineering University of California San Diego La Jolla California Halicioğlu Data Science Institute University of California San Diego La Jolla California Halicioğlu Data Science Institute University of California San Diego La Jolla California and Scripps Institution of Oceanography University of California San Diego La Jolla California

Multi-fidelity surrogate modeling aims to learn an accurate surrogate at the highest fidelity level by combining data from multiple sources. Traditional methods relying on Gaussian processes can hardly scale to high-dimensional data. Deep learning approaches utilize neural network based encoders and decoders to improve scalability. These approaches share encoded representations across fidelities without including corresponding decoder parameters. This hinders inference performance, especially in out-of-distribution scenarios when the highest fidelity data has limited domain coverage. To address these limitations, we propose Multi-fidelity Residual Neural Processes (MFRNP), a novel multifidelity surrogate modeling framework. MFRNP explicitly models the residual between the aggregated output from lower fidelities and ground truth at the highest fidelity. The aggregation introduces decoders into the information sharing step and optimizes lower fidelity decoders to accurately capture both in-fidelity and crossfidelity information. We show that MFRNP significantly outperforms state-of-the-art in learning partial differential equations and a real-world climate modeling task. Our code is published at: ***/Rose-STL-Lab/MFRNP.

关键词：

Full Bayesian Significance Testing for Neural Networks

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Liu, Zehua Li, Zimeng Wang, Jingyuan He, Yue School of Computer Science and Engineering Beihang University Beijing China School of Economics and Management Beihang University Beijing China Key Laboratory of Data Intelligence and Management Beihang University Ministry of Industry and Information Technology Beijing China Department of Computer Science and Technology Tsinghua University Beijing China

Significance testing aims to determine whether a proposition about the population distribution is the truth or not given observations. However, traditional significance testing often needs to derive the distribution of the testing statistic, failing to deal with complex nonlinear relationships. In this paper, we propose to conduct Full Bayesian Significance Testing for neural networks, called nFBST, to overcome the limitation in relationship characterization of traditional approaches. A Bayesian neural network is utilized to fit the nonlinear and multi-dimensional relationships with small errors and avoid hard theoretical derivation by computing the evidence value. Besides, nFBST can test not only global significance but also local and instance-wise significance, which previous testing methods don’t focus on. Moreover, nFBST is a general framework that can be extended based on the measures selected, such as Grad-nFBST, LRP-nFBST, DeepLIFT-nFBST, LIME-nFBST. A range of experiments on both simulated and real data are conducted to show the advantages of our method. Copyright © 2024, The Authors. All rights reserved.

关键词： Lime

INSTANCE-DEPENDENT REGRET ANALYSIS OF KERNELIZED BANDITS

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Shekhar, Shubhanshu Javidi, Tara Department of Statistics and Data Science CMU United States Department of Electrical and Computer Engineering UCSD United States

We study the kernelized bandit problem, that involves designing an adaptive strategy for querying a noisy zeroth-order-oracle to efficiently learn about the optimizer of an unknown function f with a norm bounded by M ... 详细信息

关键词： Machine learning

Design and Implementation of an active safety system for Vehicular Ad-Hoc Networks(VANETs)

学校读者我要写书评

暂无评论

Design and Implementation of an active safety system for Veh...

International Conference on Information Networking

作者： Halimjon Hujamatov Debasis Das Amir Lazarev Ernazar Reypnazarov Doston Khasaniv Ankur Nahar Data Communication Networks and Systems Department Tashkent University of Information Technologies Named After Muhammad al-Khwarizmi Tashkent Uzbekistan Department of Computer Science and Engineering Indian Institite of Technology Jodhpur Rajasthan India

ISBN: (数字)9798350330946

ISBN: (纸本)9798350330953

Vehicular communication, underpinned by IEEE 802.11p/WAVE-based Vehicle Ad-hoc Networks (VANETs), is instrumental in the seamless functioning of intra-vehicle exchanges. However, a comprehensive assessment of these systems reveals suboptimal efficiencies at the data layer, specifically regarding default broadcast intervals. Such inefficiencies lead to escalated packet collisions and subpar utilization of the delay time counter—factors that undermine the synergistic interplay between Active Safety Systems (ASS), such as Adaptive Cruise Control (ACC), and their passive safety counterparts. To address these intricacies, this research proposes an innovative mathematical framework tailored for the IEEE 802.11p MAC layer. We propose a model that elucidates the intricate dynamics of the delay time counter and offers refined broadcast intervals buttressed by robust algorithmic strategies. Empirical evaluations, conducted in meticulously simulated vehicular environments, validate the prowess of the proposed paradigm, highlighting a decline in packet collision instances. Quantitative findings from this research evince a notable decrease in packet collision rates and a commensurate enhancement in communication reliability, pivotal for advanced vehicular systems. Such technical augmentations directly elevate the operational reliability of cutting-edge safety mechanisms, exemplified by systems like the Toyota Pre-Crash Safety System.

关键词： Heuristic algorithms Instruments Vehicular ad hoc networks Physical layer Road safety Mathematical models Safety

Segment Together: A Versatile Paradigm for Semi-Supervised Medical Image Segmentation

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Zeng, Qingjie Xie, Yutong Lu, Zilin Lu, Mengkang Wu, Yicheng Xia, Yong School of Computer Science and Engineering Northwestern Polytechnical University China Australian Institute for Machine Learning University of Adelaide Australia Department of Data Science & AI Faculty of Information Technology Monash University Australia

Annotation scarcity has become a major obstacle for training powerful deep-learning models for medical image segmentation, restricting their deployment in clinical scenarios. To address it, semi-supervised learning by exploiting abundant unlabeled data is highly desirable to boost the model training. However, most existing works still focus on limited medical tasks and underestimate the potential of learning across diverse tasks and multiple datasets. Therefore, in this paper, we introduce a Versatile Semi-supervised framework (VerSemi) to point out a new perspective that integrates various tasks into a unified model with a broad label space, to exploit more unlabeled data for semi-supervised medical image segmentation. Specifically, we introduce a dynamic task-prompted design to segment various targets from different datasets. Next, this unified model is used to identify the foreground regions from all labeled data, to capture cross-dataset semantics. Particularly, we create a synthetic task with a cutmix strategy to augment foreground targets within the expanded label space. To effectively utilize unlabeled data, we introduce a consistency constraint. This involves aligning aggregated predictions from various tasks with those from the synthetic task, further guiding the model in accurately segmenting foreground regions during training. We evaluated our VerSemi model on four public benchmarking datasets. Extensive experiments demonstrated that VerSemi can consistently outperform the second-best method by a large margin (e.g., an average 2.69% Dice gain on four datasets), setting new SOTA performance for semi-supervised medical image segmentation. The code will be released. © 2023, CC BY.

关键词： Semantics

Robin: A Novel Method to Produce Robust Interpreters for Deep Learning-Based Code Classifiers

学校读者我要写书评

暂无评论

Robin: A Novel Method to Produce Robust Interpreters for Dee...

IEEE International Conference on Automated Software engineering (ASE)

作者： Zhen Li Ruqian Zhang Deqing Zou Ning Wang Yating Li Shouhuai Xu Chen Chen Hai Jin School of Cyber Science and Engineering Huazhong University of Science and Technology Wuhan China Services Computing Technology and System Lab Hubei Key Laboratory of Distributed System Security Cluster and Grid Computing Lab National Engineering Research Center for Big Data Technology and System Hubei Engineering Research Center on Big Data Security Department of Computer Science University of Colorado Colorado Springs USA Center for Research in Computer Vision University of Central Florida USA School of Computer Science and Technology Huazhong University of Science and Technology Wuhan China

Deep learning has been widely used in source code classification tasks, such as code classification according to their functionalities, code authorship attribution, and vulnerability detection. Unfortunately, the black-box nature of deep learning makes it hard to interpret and understand why a classifier (i.e., classification model) makes a particular prediction on a given example. This lack of interpretability (or explainability) might have hindered their adoption by practitioners because it is not clear when they should or should not trust a classifier's prediction. The lack of interpretability has motivated a number of studies in recent years. However, existing methods are neither robust nor able to cope with out-of-distribution examples. In this paper, we propose a novel method to produce Robust interpreters for a given deep learning-based code classifier; the method is dubbed Robin. The key idea behind Robin is a novel hybrid structure combining an interpreter and two approximators, while leveraging the ideas of adversarial training and data augmentation. Experimental results show that on average the interpreter produced by Robin achieves a 6.11% higher fidelity (evaluated on the classifier), 67.22% higher fidelity (evaluated on the approximator), and 15.87x higher robustness than that of the three existing interpreters we evaluated. Moreover, the interpreter is 47.31% less affected by out-of-distribution examples than that of LEMNA.

关键词：