检索结果-内蒙古大学图书馆

41st International Conference on Machine Learning, ICML 2024

作者： Yu, Runsheng Zhang, Youzhi Kwok, James T. Department of Computer Science and Engineering The Hong Kong University of Science and Technology Hong Kong Centre for Artificial Intelligence and Robotics Hong Kong Institute of Science & Innovation CAS Hong Kong

Sharpness-Aware Minimization (SAM), which performs gradient descent on adversarially perturbed weights, can improve generalization by identifying flatter minima. However, recent studies have shown that SAM may suffer from convergence instability and oscillate around saddle points, resulting in slow convergence and inferior performance. To address this problem, we propose the use of a lookahead mechanism to gather more information about the landscape by looking further ahead, and thus find a better trajectory to converge. By examining the nature of SAM, we simplify the extrapolation procedure, resulting in a more efficient algorithm. Theoretical results show that the proposed method converges to a stationary point and is less prone to saddle points. Experiments on standard benchmark datasets also verify that the proposed method outperforms the SOTAs, and converge more effectively to flat minima. Copyright 2024 by the author(s)

关键词：

来源：评论

学校读者我要写书评

暂无评论

引用

33rd ACM Web Conference, WWW 2024

作者： Ma, Changyi Yu, Runsheng Zhang, Youzhi Centre for Artificial Intelligence and Robotics Hong Kong Institute of Science and Innovation CAS Hong Kong Department of Computer Science and Engineering Hong Kong University of Science and Technology Hong Kong

ISBN: (纸本)9798400701719

The similarity matrix is at the core of similarity search problems. However, incomplete observations are ubiquitous in real scenarios leading to a less accurate similarity matrix. To alleviate this problem, in this paper, based on the key insight that the similarity matrix enjoys both the symmetric and positive semi-definiteness (PSD) properties, we propose a novel similarity matrix calibration method, which is scalable, effective, and sound. Specifically, we establish the PSD property as a constraint for the similarity matrix calibration problem and propose a novel similarity matrix calibration method to estimate the similarity matrix, which approximates the unknown complete ground-truth similarity matrix. To enable a fast optimization process, we further develop a general approximated algorithm that bypasses the computation of singular values. Theoretical analysis ensures stable calibration performance and convergence speed. Extensive experiments of similarity matrix calibration on real-world datasets demonstrate that our proposed method outperforms baseline methods in terms of both accuracy and speed. © 2024 ACM.

关键词： Calibration

来源：评论

学校读者我要写书评

暂无评论

Arbitrarily Scalable Environment Generators via Neural Cellular Automata (Extended Abstract) 17th

Arbitrarily Scalable Environment Generators via Neural Cellu...

引用

17th International Symposium on Combinatorial Search, SoCS 2024

作者： Zhang, Yulun Fontaine, Matthew C. Bhatt, Varun Nikolaidis, Stefanos Li, Jiaoyang Robotics Institute Carnegie Mellon University United States Thomas Lord Department of Computer Science University of Southern California United States

ISBN: (纸本)9781577358916

We study the problem of generating arbitrarily large environments to improve the throughput of multi-robot systems. Prior work proposes Quality Diversity (QD) algorithms as an effective method for optimizing the environments of automated warehouses. However, these approaches optimize only relatively small environments, falling short when it comes to replicating real-world warehouse sizes. The challenge arises from the exponential increase in the search space as the environment size increases. Additionally, the previous methods have only been tested with up to 350 robots in simulations, while practical warehouses could host thousands of robots. In this paper, instead of optimizing environments, we propose to optimize Neural Cellular Automata (NCA) environment generators via QD algorithms. We train a collection of NCA generators with QD algorithms in small environments and then generate arbitrarily large environments from the generators at test time. We show that NCA environment generators maintain consistent, regularized patterns regardless of environment size, significantly enhancing the scalability of multi-robot systems in two different domains with up to 2,350 robots. Additionally, we demonstrate that our method scales a single-agent reinforcement learning policy to arbitrarily large environments with similar patterns. We include the source code at https://***/lunjohnzhang/warehouse_env_gen_nca_public. © 2024, Association for the Advancement of Artificial Intelligence (***). All rights reserved.

关键词： Multipurpose robots

来源：评论

学校读者我要写书评

暂无评论

EDSD: efficient driving scenes detection based on Swin Transformer

引用

Multimedia Tools and Applications 2024年第39期83卷 87179-87198页

作者： Chen, Wei Zheng, Ruihan Jiang, Jiade Tian, Zijian Zhang, Fan Liu, Yi Beijing100083 China Key Laboratory of Intelligent Mining and Robotics Ministry of Emergency Management Beijing100083 China School of Computer Science & amp Technology China University of Mining and Technology Xuzhou221116 China

In the field of autonomous driving, the detection of targets such as vehicles, bicycles, and pedestrians in complex road conditions is of great importance. Through extensive experimentation, we have found that various vehicle targets generally occupy large sizes in the image but are easily occluded, while small targets such as pedestrians usually appear densely. The detection of targets of different sizes is an important challenge for the performance of current detectors. To address this issue, we proposed a novel hierarchical feature pyramid network structure. This structure comprises a series of CNN-Transformer variant layers, each of which is a superposition of CST neural network modules and Swin Transformer modules. In addition, considering that the huge computation of the global self-attention mechanism is difficult to be applied in the field of autonomous driving, we adopted the shifted window method in SwinFM, which effectively accelerates the inference process by replacing the traditional method by using the self-attention mechanism within the window. This study uses the Swin Transformer as a baseline. Compared to the baseline, our EDSD model improves the average accuracy by 1.8% and 3.1% on the BDD100K dataset and the KITTI dataset, respectively. © The Author(s), under exclusive licence to Springer science+Business Media, LLC, part of Springer Nature 2024.

关键词： Object detection

来源：评论

学校读者我要写书评

暂无评论

i-Glove: An Intelligent Glove System Based on Deep Learning to Support Deaf-blind Individuals in Recognizing Banknotes 3

i-Glove: An Intelligent Glove System Based on Deep Learning ...

引用

3rd IEEE International Conference on robotics, Automation, Artificial-Intelligence and Internet-of-Things, RAAICON 2024

作者： Hossain, Fahad Mohammad Alavi, Rafit Safat, Yeamin Sarker, Gobinda Chandra Noor, Nafisa Hossain, Ekram Mymensingh Engineering College Department of Computer Science and Engineering Mymensingh Bangladesh University of Dhaka Department of Robotics and Mechatronics Engineering Dhaka Bangladesh

ISBN: (纸本)9798331534400

The deaf-blind community faces significant challenges in identifying banknotes due to simultaneous hearing and vision impairments, which complicate their ability to conduct daily financial transactions. Recent advances in Artificial Intelligence (AI)-based assistive technologies offer promising potential to address these challenges. This study presents the "i-Glove,"a wearable device specifically developed to assist the deaf-blind community in Bangladesh with accurate banknote identification. The i-Glove is designed to recognize nine common Bangladeshi banknotes (e.g., BDT 20, 50, 100) through a camera module integrated on the palmar side of the glove, which captures real-time images of the banknotes. These images are then processed by a convolutional neural network (CNN) model to accurately classify each banknote. Identified notes are translated into unique vibration patterns that are delivered to the user through a shaftless vibration motor embedded in the glove, providing intuitive, non-visual communication. Compared to previous approaches, our model demonstrates superior performance even with a compact dataset, achieving an overall F1-score accuracy of 96.55%, with class-specific precision, recall, and F1-score metrics ranging from 90% to 100%. Additionally, a dedicated application is developed which supports real-time banknote detection and interfaces seamlessly with the glove. The proposed system represents a significant step forward in assistive technology for the deaf-blind community, empowering the users with greater autonomy in financial transactions. © 2024 IEEE.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Multi-Robot Coordination and Layout Design for Automated Warehousing (Extended Abstract) 17th

Multi-Robot Coordination and Layout Design for Automated War...

引用

17th International Symposium on Combinatorial Search, SoCS 2024

ISBN: (纸本)9781577358916

With the rapid progress in Multi-Agent Path Finding (MAPF), researchers have studied how MAPF algorithms can be deployed to coordinate hundreds of robots in large automated warehouses. While most works try to improve the throughput of such warehouses by developing better MAPF algorithms, we focus on improving the throughput by optimizing the warehouse layout. We show that, even with state-of-the-art MAPF algorithms, commonly used human-designed layouts can lead to congestion for warehouses with large numbers of robots and thus have limited scalability. We extend existing automatic scenario generation methods to optimize warehouse layouts. Results show that our optimized warehouse layouts (1) reduce traffic congestion and thus improve throughput, (2) improve the scalability of the automated warehouses by doubling the number of robots in some cases, and (3) are capable of generating layouts with user-specified diversity measures. We include the source code at: https://***/lunjohnzhang/warehouse_env_gen_public. © 2024, Association for the Advancement of Artificial Intelligence (***). All rights reserved.

关键词： Warehouses

来源：评论

学校读者我要写书评

暂无评论

Active Perception for Grasp Detection via Neural Graspness Field 38

Active Perception for Grasp Detection via Neural Graspness F...

引用

38th Conference on Neural Information Processing Systems, NeurIPS 2024

作者： Ma, Haoxiang Shi, Modi Gao, Boyang Huang, Di State Key Laboratory of Complex and Critical Software Environment School of Computer Science and Engineering Beihang University Beijing China Geometry Robotics

This paper tackles the challenge of active perception for robotic grasp detection in cluttered environments. Incomplete 3D geometry information can negatively affect the performance of learning-based grasp detection methods, and scanning the scene from multiple views introduces significant time costs. To achieve reliable grasping performance with efficient camera movement, we propose an active grasp detection framework based on the Neural Graspness Field (NGF), which models the scene incrementally and facilitates next-best-view planning. Constructed in real-time as the camera moves, the NGF effectively models the grasp distribution in 3D space by rendering graspness predictions from each view. For next-best-view planning, we aim to reduce the uncertainty of the NGF through a graspness inconsistency-guided policy, selecting views based on discrepancies between NGF outputs and a pre-trained graspness network. Additionally, we present a neural graspness sampling method that decodes graspness values from the NGF to improve grasp pose detection results. Extensive experiments on the GraspNet-1Billion benchmark demonstrate significant performance improvements compared to previous works. Real-world experiments show that our method achieves a superior trade-off between grasping performance and time costs. Code is available at https://***/mahaoxiang822/ActiveNGF. © 2024 Neural information processing systems foundation. All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

MF-BERT: A Siamese Pre-training Framework for Motion Forecasting

MF-BERT: A Siamese Pre-training Framework for Motion Forecas...

引用

2025 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2025

作者： Shi, Jianxin Chen, Jinhao Chen, Xiaolong Ma, Jun Wo, Tianyu School of Computer Science and Engineering Beihang University Beijing China Robotics and Autonomous Systems Thrust The Hong Kong University of Science and Technology Guangzhou China

ISBN: (纸本)9798350368741

Accurately predicting the future motions of traffic agents is essential for autonomous systems. Despite the significant success of existing motion forecasting methods based on supervised learning, they still exhibit two main limitations. First, when annotated data for a scene is limited, these methods often fail to achieve the expected accuracy. Second, they typically rely on complex architectures and extensive prior knowledge to improve performance. To overcome these challenges, we propose MF-BERT, a novel framework that adapts the concept of BERT to motion forecasting, inspired by advancements in the self-supervised pre-training paradigm. During pre-training, we design a siamese sequence modeling task with an asymmetric mask strategy to capture complex behavior patterns of agents. During fine-tuning, the pre-trained representation module initializes the feature encoder of the motion forecasting model, and a multimodal trajectory decoder generates all possible predictions. Experimental results demonstrate the superiority of MF-BERT over state-of-the-art methods. © 2025 IEEE.

关键词： Autonomous Motion Forecasting Self-supervised Learning Time Series Analysis

来源：评论

学校读者我要写书评

暂无评论

A Review of Deep Learning Techniques for Glaucoma Detection

引用

SN computer science 2023年第3期4卷 274页

作者： Guergueb, Takfarines Akhloufi, Moulay A. Perception Robotics and Intelligent Machines Research Group (PRIME) Computer Science Department Université de Moncton Moncton NB Canada

Glaucoma is one of the major reasons for visual impairment all across the globe. The recent advancements in machine learning techniques have greatly facilitated ophthalmologists in the early diagnosis of ocular diseases through the employment of automated systems. Several studies have been published lately to address the timely detection of glaucoma using deep learning approaches. A comprehensive review of the deep learning approaches employed for glaucoma detection using retinal fundus images is presented in this paper. The available retinal image datasets, image pre-processing techniques, state-of-the-art models, and performance evaluation metrics used in the recent studies are reviewed. This systematic review aims to provide critical insights and potential research directions to the ophthalmologists and researchers in this domain. © 2023, The Author(s), under exclusive licence to Springer Nature Singapore Pte Ltd.

关键词： Deep learning Eye diseases Glaucoma Image processing Machine learning Ophthalmology Transfer learning

来源：评论

学校读者我要写书评

暂无评论

The ATTUNE Model for Artificial Trust Towards Human Operators

The ATTUNE Model for Artificial Trust Towards Human Operator...

引用

2024 IEEE International Conference on Systems, Man, and Cybernetics, SMC 2024

作者： Petousakis, Giannis Cangelosi, Angelo Stolkin, Rustam Chiou, Manolis University of Manchester Cognitive Robotics Lab Department of Computer Science United Kingdom University of Birmingham School of Metallurgy and Materials Extreme Robotics Lab United Kingdom Queen Mary University of London United Kingdom

ISBN: (纸本)9781665410205

This paper presents a novel method to quantify Trust in HRI. It proposes an HRI framework for estimating the Robot Trust towards the Human in the context of a narrow and specified task. The framework produces a real-time estimation of an AI agent's Artificial Trust towards a Human partner interacting with a mobile teleoperation robot. The approach for the framework is based on principles drawn from Theory of Mind, including information about the human state, action, and intent. The framework creates the ATTUNE model for Artificial Trust Towards Human Operators. The model uses metrics on the operator's state of attention, navigational intent, actions, and performance to quantify the Trust towards them. The model is tested on a pre-existing dataset that includes recordings (ROSbags) of a human trial in a simulated disaster response scenario. The performance of ATTUNE is evaluated through a qualitative and quantitative analysis. The results of the analyses provide insight into the next stages of the research and help refine the proposed approach. © 2024 IEEE.

关键词： Chatbots

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：