检索结果-内蒙古大学图书馆

2024 International Conference on Intelligent Communication, Sensing and Electromagnetics, ICSE 2024

作者： Du, Heng Cang, Huaiming Bai, Yiwen Wang, Xinyi Beijing Elephant Technology Co. Ltd Beijing China School of Transportation Science and Engineering Beihang University Beijing102206 China State Key Lab of Intelligent Transportation System Beijing100191 China School of Mechanical Engineering Tianjin University of Technology Tianjin Key Laboratory for Advanced Mechanical System Design and Intelligent Control Tianjin China National Demonstration Center for Experimental Mechanical and Electrical Engineering Education Tianjin300384 China

ISBN: (纸本)9798350354935

In the field of railway transportation, with the continuous improvement of train running speed and the continuous increase of operating mileage, it becomes particularly important to ensure the safety and integrity of small-Target infrastructure along the railway train. Although many small-Target detection methods have been proposed, the research on small-Target infrastructure detection along rail trains is very rare. To solve this problem, this paper proposes a small-Target infrastructure detection network with spatial tracking and multi-level feature extraction based on Yolov8n. The experimental results show that ST-YOLO has a 3.6% mAP improvement on the OSDaR23 dataset compared to the baseline Yolov8n, and shows significant advantages over other state-of-The-Art methods. © 2024 IEEE.

关键词： Railroads

来源：评论

学校读者我要写书评

暂无评论

Contactless Detection of Mouse's Licking with a 120 GHz Interferometric Radar 9

Contactless Detection of Mouse's Licking with a 120 GHz Inte...

引用

9th IEEE MTT-S International Wireless Symposium, IWS 2022

作者： Ma, Lina Wen, Li Qu, Xuetong Gu, Changzhan Mao, Junfa Shanghai Jiao Tong University MoE Key Lab of High-Speed Electronic Systems MoE Key Lab of Artificial Intelligence Shanghai200240 China Institute of Neuroscience Chinese Academy of Sciences State Key Laboratory of Neuroscience Center for Excellence in Brain Science and Intelligence Technology Shanghai200031 China

ISBN: (数字)9781665481977

ISBN: (纸本)9781665481977

Accurate quantification of behavior has positive in-fluence on the understanding of brain. It is important to monitor movement behaviors for subjects like human and animals. In this paper, a contactless technique for detecting mouse's licking using a custom-designed 120 GHz millimeter-wave radar sensing system is proposed. The experimental scene to test the cognitive judg-ments of mouse is also given. Owing to the miniaturized size, the radar sensor could be placed on the water needle and close to the tongue of mouse without blocking the mouse's sight in a virtual space. The system has been validated and the experimental results show that the movement situations of mouse could be distin-guished precisely based on the proposed technique, such as licking, running on the scroll wheel and touching needle with paws. The detection technique of the behavioral state of mouse lays the groundwork for the study of subsequent association of animal movement and perception. © 2022 IEEE.

关键词： Needles

来源：评论

学校读者我要写书评

暂无评论

Container lifecycle-aware scheduling for serverless computing

Container lifecycle-aware scheduling for serverless computin...

引用

作者： Wu, Song Tao, Zhiheng Fan, Hao Huang, Zhuo Zhang, Xinmin Jin, Hai Yu, Chen Cao, Chun 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 Wuhan China State Key Laboratory for Novel Software Technology Department of Computer Science and Technology Nanjing University Nanjing China

Elastic scaling in response to changes on demand is a main benefit of serverless computing. When bursty workloads arrive, a serverless platform launches many new containers and initializes function environments (known as cold starts), which incurs significant startup latency. To reduce cold starts, platforms usually pause a container after it serves a request, and reuse this container for subsequent requests. However, this reuse strategy cannot efficiently reduce cold starts because the schedulers are agnostic of container lifecycle. For example, it may ignore soon available containers or evict soon needed containers. We propose a container lifecycle-aware scheduling strategy for serverless computing, CAS. The key idea is to control distribution of requests and determine creation or eviction of containers according to different lifecycle phases of containers. We implement a prototype of CAS on OpenWhisk. Our evaluation shows that CAS reduces 81% cold starts and therefore brings a 63% reduction at 95th percentile latency compared with native scheduling strategy in OpenWhisk when there is worker contention between workloads, and does not add significant performance overhead. © 2021 John Wiley & Sons Ltd.

关键词： Containers

来源：评论

学校读者我要写书评

暂无评论

Token Compensator: Altering Inference Cost of Vision Transformer without Re-Tuning

arXiv

引用

arXiv 2024年

作者： Jie, Shibo Tang, Yehui Guo, Jianyuan Deng, Zhi-Hong Han, Kai Wang, Yunhe State Key Laboratory of General Artificial Intelligence School of Intelligence Science and Technology Peking University China Huawei Noah’s Ark Lab Hong Kong

Token compression expedites the training and inference of Vision Transformers (ViTs) by reducing the number of the redundant tokens, e.g., pruning inattentive tokens or merging similar tokens. However, when applied to downstream tasks, these approaches suffer from significant performance drop when the compression degrees are mismatched between training and inference stages, which limits the application of token compression on off-the-shelf trained models. In this paper, we propose a model arithmetic framework to decouple the compression degrees between the two stages. In advance, we additionally perform a fast parameter-efficient self-distillation stage on the pre-trained models to obtain a small plugin, called Token Compensator (ToCom), which describes the gap between models across different compression degrees. During inference, ToCom can be directly inserted into any downstream off-the-shelf models with any mismatched training and inference compression degrees to acquire universal performance improvements without further training. Experiments on over 20 downstream tasks demonstrate the effectiveness of our framework. On CIFAR100, fine-grained visual classification, and VTAB-1k, ToCom can yield up to a maximum improvement of 2.3%, 1.5%, and 2.0% in the average performance of DeiT-B, respectively.† © 2024, CC0.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Language Models Hallucinate, but May Excel at Fact Verification

Language Models Hallucinate, but May Excel at Fact Verificat...

引用

2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, NAACL 2024

作者： Guan, Jian Dodge, Jesse Wadden, David Huang, Minlie Peng, Hao The CoAI group DCST Institute for Artificial Intelligence China State Key Lab of Intelligent Technology and Systems China Beijing National Research Center for Information Science and Technology China Tsinghua University Beijing100084 China Allen Institute for AI United States University of Illinois Urbana-Champaign United States

ISBN: (纸本)9798891761148

Recent progress in natural language processing (NLP) owes much to remarkable advances in large language models (LLMs). Nevertheless, LLMs frequently "hallucinate," resulting in non-factual outputs. Our carefully-designed human evaluation substantiates the serious hallucination issue, revealing that even GPT-3.5 produces factual outputs less than 25% of the time. This underscores the importance of fact verifiers in order to measure and incentivize progress. Our systematic investigation affirms that LLMs can be repurposed as effective fact verifiers with strong correlations with human judgments. Surprisingly, FLAN-T511B, the least factual generator in our study, performs the best as a fact verifier, even outperforming more capable LLMs like GPT3.5 and ChatGPT. Delving deeper, we analyze the reliance of these LLMs on high-quality evidence, as well as their deficiencies in robustness and generalization ability. Our study presents insights for developing trustworthy generation models. © 2024 Association for Computational Linguistics.

关键词： Computational linguistics

来源：评论

学校读者我要写书评

暂无评论

An Inclusive Theoretical Framework of Robust Supervised Contrastive Loss against label Noise

arXiv

引用

arXiv 2025年

作者： Cui, Jingyi Zhang, Yi-Ge Liu, Hengyu Wang, Yisen The State Key Lab of General Artificial Intelligence School of Intelligence Science and Technology Peking University China The Department of Electronic Engineering The Chinese University of Hong Kong Hong Kong

Learning from noisy labels is a critical challenge in machine learning, with vast implications for numerous real-world scenarios. While supervised contrastive learning has recently emerged as a powerful tool for navigating label noise, many existing solutions remain heuristic, often devoid of a systematic theoretical foundation for crafting robust supervised contrastive losses. To address the gap, in this paper, we propose a unified theoretical framework for robust losses under the pairwise contrastive paradigm. In particular, we for the first time derive a general robust condition for arbitrary contrastive losses, which serves as a criterion to verify the theoretical robustness of a supervised contrastive loss against label noise. The theory indicates that the popular InfoNCE loss is in fact non-robust, and accordingly inspires us to develop a robust version of InfoNCE, termed Symmetric InfoNCE (SymNCE). Moreover, we highlight that our theory is an inclusive framework that provides explanations to prior robust techniques such as nearest-neighbor (NN) sample selection and robust contrastive loss. Validation experiments on benchmark datasets demonstrate the superiority of SymNCE against label noise. Copyright © 2025, The Authors. All rights reserved.

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

HRVDA: High-Resolution Visual Document Assistant

arXiv

引用

arXiv 2024年

作者： Liu, Chaohu Yin, Kun Cao, Haoyu Jiang, Xinghua Li, Xin Liu, Yinsong Jiang, Deqiang Sun, Xing Xu, Linli School of Computer Science and Technology University of Science and Technology China State Key Laboratory of Cognitive Intelligence China Tencent YouTu Lab China

Leveraging vast training data, multimodal large language models (MLLMs) have demonstrated formidable general visual comprehension capabilities and achieved remarkable performance across various tasks. However, their performance in visual document understanding still leaves much room for improvement. This discrepancy is primarily attributed to the fact that visual document understanding is a fine-grained prediction task. In natural scenes, MLLMs typically use low-resolution images, leading to a substantial loss of visual information. Furthermore, general-purpose MLLMs do not excel in handling document-oriented instructions. In this paper, we propose a High-Resolution Visual Document Assistant (HRVDA), which bridges the gap between MLLMs and visual document understanding. This model employs a content filtering mechanism and an instruction filtering module to separately filter out the content-agnostic visual tokens and instruction-agnostic visual tokens, thereby achieving efficient model training and inference for high-resolution images. In addition, we construct a document-oriented visual instruction tuning dataset and apply a multi-stage training strategy to enhance the model's document modeling capabilities. Extensive experiments demonstrate that our model achieves state-of-the-art performance across multiple document understanding datasets, while maintaining training efficiency and inference speed comparable to low-resolution models. Copyright © 2024, The Authors. All rights reserved.

关键词： Visual languages

来源：评论

学校读者我要写书评

暂无评论

A Drosophila-inspired intelligent olfactory biomimetic sensing system for gas recognition in complex environments

引用

Microsystems & Nanoengineering 2024年第5期10卷 319-330页

作者： Xiawei Yue Jiachuang Wang Heng Yang Zening Li Fangyu Zhao Wenyuan Liu Pingping Zhang Hong Chen Hanjun Jiang Nan Qin Tiger H.Tao State Key Laboratory of Transducer Technology Shanghai Institute of Microsystem and Information TechnologyChinese Academy of SciencesShanghai 200050China School of Graduate Study University of Chinese Academy of SciencesBeijing 100049China Suzhou Huiwen Nanotechnology Co.Ltd. Jiangsu 215004China School of Integrated Circuits Tsinghua UniversityBeijing 100084China Center of Materials Science and Optoelectronics Engineering University of Chinese Academy of SciencesBeijing 100049China 2020 X-Lab Shanghai Institute of Microsystem and Information TechnologyChinese Academy of SciencesShanghai 200050China Center for Excellence in Brain Science and Intelligence Technology Chinese Academy of SciencesShanghai 200031China Neuroxess Co.Ltd.(Jiangxi) NanchangJiangxi 330029China Guangdong Institute of Intelligence Science and Technology HengqinZhuhaiGuangdong 519031China OTianqiao and Chrissy Chen Institute for Translational Research ShanghaiChina

The olfactory sensory system of Drosophila has several advantages,including low power consumption,high rapidity and high ***,we present a biomimetic intelligent olfactory sensing system based on the integration of an 18-channel microelectromechanical system(MEMS)sensor array(16 gas sensors,1 humidity sensor and 1 temperature sensor),a complementary metal-oxide-semiconductor(CMOS)circuit and an olfactory lightweight machine-learning algorithm inspired by *** system is an artificial version of the biological olfactory perception system with the capabilities of environmental sensing,multi-signal processing,and odor *** olfactory data are processed and reconstructed by the combination of a shallow neural network and a residual neural network,with the aim to determine the noxious gas information in challenging environments such as high humidity scenarios and partially damaged sensor *** a result,our electronic olfactory sensing system is capable of achieving comprehensive gas recognition by qualitatively identifying 7 types of gases with an accuracy of 98.5%,reducing the number of parameters and the difficulty of calculation,and quantitatively predicting each gas of 3-5 concentration gradients with an accuracy of 93.2%;thus,these results show superiority of our system in supporting alarm systems in emergency rescue scenarios.

关键词： system environments humidity

来源：评论

学校读者我要写书评

暂无评论

Multi-Temporal PolSAR Image Classification Based on Polarimetric Scattering Tensor Eigenvalue Decomposition and Deep CNN Model

Multi-Temporal PolSAR Image Classification Based on Polarime...

引用

2022 IEEE International Conference on Signal Processing, Communications and Computing, ICSPCC 2022

作者： Deng, Jun-Wu Li, Hao-Liang Cui, Xing-Chao Chen, Si-Wei National University of Defense Technology The State Key Lab. of Complex Electromagnetic Environ. Effects On Electronics and Information System Changsha410073 China

ISBN: (数字)9781665469722

ISBN: (纸本)9781665469722

Multi-temporal polarimetric synthetic aperture radar (PolSAR) image is an important tool to monitor crops growth and evaluate disaster damage. The multi-temporal PolSAR data has the high dimensional representation. Benefited from the tensor analysis, a three dimensional polarimetric scattering tensor is established. The polarimetric scattering tensor eigenvalue decomposition is proposed to derive the polarimetric features, which are polarimetric tensor entropy, polarimetric tensor alpha angle and polarimetric tensor anisotropy, respectively. Multi-temporal PolSAR image classification is applied to validate the effectiveness of the proposed features. To further improve the classification accuracy, the 1 × 1 convolutional kernel is introduced to learn the inter-temporal information. For the multi-temporal UAVSAR datasets, the proposed method achieves the excellent classification accuracy in the multi-temporal PolSAR image classification. © 2022 IEEE.

关键词： Image classification

来源：评论

学校读者我要写书评

暂无评论

Research on the Scattering Characteristics of the Van Atta Cube Scatterer

Research on the Scattering Characteristics of the Van Atta C...

引用

2022 International Applied Computational Electromagnetics Society Symposium, ACES-China 2022

作者： Gan, Lin Wu, Zehao Li, Jianbing National University of Defense Technology The State Key Lab. of Complex Electromagnetic Environ. Effects on Electronics and Information System College of Electronic Science and Technology Changsha China

ISBN: (纸本)9781665452366

In order to realize good omnidirectional backtracking of electromagnetic waves, a Van Atta cube scatterer consists of six identical Van Atta plane arrays is proposed. In this paper, the scattering characteristics in different incident directions are emphatically studied. Simulation results show that the Van Atta cube scatterer has the advantage of omnidirectional scattering, with the effective backtracking angle range exceeding 77% of the whole angle domain. © 2022 IEEE.

关键词： Geometry

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：