检索结果-内蒙古大学图书馆

IsoVISoR: Towards 3D Mesoscale Brain Mapping of Large Mammals at Isotropic Sub-micron Resolution

Neuroscience Bulletin 2025年第2期41卷 344-348页

作者： Chao-Yu Yang Yan Shen Xiaoyang Qi Lufeng Ding Yanyang Xiao Qingyuan Zhu Hao Wang Cheng Xu Pak-Ming Lau Pengcheng Zhou Fang Xu Guo-Qiang Bi Division of Life Sciences and Medicine CAS Key Laboratory of Brain Function and DiseaseUniversity of Science and Technology of ChinaHefei230026China Interdisciplinary Center for Brain Information Shenzhen-Hong Kong Institute of Brain ScienceShenzhen Institute of Advanced TechnologyChinese Academy of SciencesShenzhen518055China Center for Integrative Imaging Hefei National Research Center for Physical Sciences at the MicroscaleUniversity of Science and Technology of ChinaHefei230027China National Engineering Laboratory for Brain-Inspired Intelligence Technology and Application MoE Key Laboratory of Brain-Inspired Intelligent Perception and CognitionSchool of Information Science and TechnologyUniversity of Science and Technology of ChinaHefei230026China Anhui Province Key Laboratory of Biomedical Imaging and Intelligent Processing Institute of Artificial IntelligenceHefei Comprehensive National Science CenterHefei230088China Faculty of Life and Health Sciences Shenzhen University of Advanced TechnologyShenzhen518107China CAS Key Laboratory of Brain Connectome and Manipulation The Brain Cognition and Brain Disease InstituteShenzhen Institute of Advanced TechnologyChinese Academy of SciencesShenzhen518055China

Dear Editor,The mammalian brain exhibits cross-scale complexity in neuronal morphology and connectivity,the study of which demands high-resolution morphological reconstruction of individual neurons across the entire brain[1-4].Current commonly used approaches for such mesoscale brain mapping include two main types of three-dimensional fluorescence microscopy:the block-face methods,and the lightsheet-based methods[5,6].In general,the high imaging speed and light efficiency of light-sheet microscopy make it a suitable tool for high-throughput volumetric imaging,especially when combined with tissue-clearing ***,large brain samples pose major challenges to this approach.

关键词： brain mapping three dimensional fluorescence microscopy mesoscale brain mapping lightsheet based methods block face methods high throughput volumetric imaging tissue clearing techniques

来源：评论

学校读者我要写书评

暂无评论

Outlier-Aware Slicing for Post-Training Quantization in Vision Transformer 41

Outlier-Aware Slicing for Post-Training Quantization in Visi...

引用

41st International Conference on Machine Learning, ICML 2024

作者： Ma, Yuexiao Li, Huixia Zheng, Xiawu Ling, Feng Xiao, Xuefeng Wang, Rui Wen, Shilei Chao, Fei Ji, Rongrong Key Laboratory of Multimedia Trusted Perception and Efficient Computing Ministry of Education of China School of Informatics Xiamen University 361005 China ByteDance Inc. China Peng Cheng Laboratory Shenzhen China Institute of Artificial Intelligence Xiamen University China

Post-Training Quantization (PTQ) is a vital technique for network compression and acceleration, gaining prominence as model sizes increase. This paper addresses a critical challenge in PTQ: the severe impact of outliers on the accuracy of quantized transformer architectures. Specifically, we introduce the concept of 'reconstruction granularity' as a novel solution to this issue, which has been overlooked in previous works. Our work provides theoretical insights into the role of reconstruction granularity in mitigating the outlier problem in transformer models. This theoretical framework is supported by empirical analysis, demonstrating that varying reconstruction granularities significantly influence quantization performance. Our findings indicate that different architectural designs necessitate distinct optimal reconstruction granularities. For instance, the multi-stage Swin Transformer architecture benefits from finer granularity, a deviation from the trends observed in ViT and DeiT models. We further develop an algorithm for determining the optimal reconstruction granularity for various ViT models, achieving state-of-the-art (SOTA) performance in PTQ. For example, applying our method to 4-bit quantization, the Swin-Base model achieves a Top-1 accuracy of 82.24% on the ImageNet classification task. This result surpasses the RepQ-ViT by 3.92% (82.24% VS 78.32%). Similarly, our approach elevates the ViT-Small to a Top-1 accuracy of 80.50%, outperforming NoisyQuant by 3.64% (80.50% VS 76.86%). 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

AFFINEQUANT: AFFINE TRANSFORMATION QUANTIZATION FOR LARGE LANGUAGE MODELS 12

AFFINEQUANT: AFFINE TRANSFORMATION QUANTIZATION FOR LARGE LA...

引用

12th International Conference on Learning Representations, ICLR 2024

The significant resource requirements associated with Large-scale Language Models (LLMs) have generated considerable interest in the development of techniques aimed at compressing and accelerating neural networks. Among these techniques, Post-Training Quantization (PTQ) has emerged as a subject of considerable interest due to its noteworthy compression efficiency and cost-effectiveness in the context of training. Existing PTQ methods for LLMs limit the optimization scope to scaling transformations between pre- and post-quantization weights. This constraint results in significant errors after quantization, particularly in low-bit configurations. In this paper, we advocate for the direct optimization using equivalent Affine transformations in PTQ (AffineQuant). This approach extends the optimization scope and thus significantly minimizing quantization errors. Additionally, by employing the corresponding inverse matrix, we can ensure equivalence between the pre- and post-quantization outputs of PTQ, thereby maintaining its efficiency and generalization capabilities. To ensure the invertibility of the transformation during optimization, we further introduce a gradual mask optimization method. This method initially focuses on optimizing the diagonal elements and gradually extends to the other elements. Such an approach aligns with the Levy-Desplanques theorem, theoretically ensuring invertibility of the transformation. As a result, significant performance improvements are evident across different LLMs on diverse datasets. Notably, these improvements are most pronounced when using very low-bit quantization, enabling the deployment of large models on edge devices. To illustrate, we attain a C4 perplexity of 15.76 (2.26↓ vs 18.02 in OmniQuant) on the LLaMA2-7B model of W4A4 quantization without overhead. On zero-shot tasks, AffineQuant achieves an average of 58.61% accuracy (1.98% ↑ vs 56.63 in OmniQuant) when using 4/4-bit quantization for LLaMA-30B, which setting a new st

关键词： Cost effectiveness

来源：评论

学校读者我要写书评

暂无评论

Reliable Observer-Based Control Against Sensor Failures for Fractional Order Systems 42

Reliable Observer-Based Control Against Sensor Failures for ...

引用

42nd Chinese Control Conference, CCC 2023

作者： Li, Bingxin Zhang, Yujie Liu, Yaowei Zhao, Xin Nankai University Institute of Robotics and Automatic Information System The Tianjin Key Laboratory of Intelligent Robotics Tianjin300071 China Institute of Intelligence Technology and Robotic Systems Shenzhen Research Institute of Nankai University Shenzhen518083 China

ISBN: (纸本)9789887581543

In the paper, stability analysis of a class of incommensurate fractional-order systems (IFOS) is studied. These sufficient conditions are based on the linear matrix inequality (LMI) and straightforwardly used to solve the feasible solutions with the LMI toolbox. Finally, two examples including a circuit example are given to illustrate the effectiveness of the proposed method, and the comparison with the previous results shows that the proposed method is less conservative. © 2023 Technical Committee on Control Theory, Chinese Association of Automation.

关键词： Linear matrix inequalities

来源：评论

学校读者我要写书评

暂无评论

Cross-Modal Retrieval for Motion and Text via DropTriple Loss 5

Cross-Modal Retrieval for Motion and Text via DropTriple Los...

引用

5th ACM International Conference on Multimedia in Asia, MMAsia 2023

作者： Yan, Sheng Liu, Yang Wang, Haoqiang Du, Xin Liu, Mengyuan Liu, Hong School of Artificial Intelligence Chongqing University of Technology China College of Computer Science Sichuan University China Key Laboratory of Machine Perception Shenzhen Graduate School Peking University China

ISBN: (纸本)9798400702051

Cross-modal retrieval of image-text and video-text is a prominent research area in computer vision and natural language processing. However, there has been insufficient attention given to cross-modal retrieval between human motion and text, despite its wide-ranging applicability. To address this gap, we utilize a concise yet effective dual-unimodal transformer encoder for tackling this task. Recognizing that overlapping atomic actions in different human motion sequences can lead to semantic conflicts between samples, we explore a novel triplet loss function called DropTriple Loss. This loss function discards false negative samples from the negative sample set and focuses on mining remaining genuinely hard negative samples for triplet training, thereby reducing violations they cause. We evaluate our model and approach on the HumanML3D and KIT Motion-Language datasets. On the latest HumanML3D dataset, we achieve a recall of 62.9% for motion retrieval and 71.5% for text retrieval (both based on R@10). The source code for our approach is publicly available at https://***/eanson023/rehamot. © 2023 Copyright held by the owner/author(s).

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

Can LLMs Replace Clinical Doctors? Exploring Bias in Disease Diagnosis by Large Language Models

Can LLMs Replace Clinical Doctors? Exploring Bias in Disease...

引用

2024 Conference on Empirical Methods in Natural Language Processing, EMNLP 2024

作者： Zhao, Yutian Wang, Huimin Liu, Yuqi Suhuang, Wu Wu, Xian Zheng, Yefeng Jarvis Research Center Tencent YouTu Lab Shenzhen China Key Laboratory of Multimedia Trusted Perception and Efficient Computing Ministry of Education of China Xiamen University China JMedical Artificial Intelligence Lab Westlake University Hangzhou China

ISBN: (纸本)9798891761681

The bias of disease prediction in Large Language Models (LLMs) is a critical yet underexplored issue, with potential implications for healthcare outcomes and equity. As LLMs increasingly find applications in healthcare, understanding and addressing their biases becomes paramount. This study focuses on this crucial topic, investigating the bias of disease prediction in models such as GPT-4, ChatGPT, and Qwen1.5-72b across gender, age range, and disease judgment behaviors.1 Utilizing a comprehensive real-clinical health record dataset of over 330,000 entries, we uncover that all three models exhibit distinct biases, indicating a pervasive issue of unfairness. To measure this, we introduce a novel metric-the diagnosis bias score, which reflects the ratio of prediction numbers to label numbers. Our in-depth analysis, based on this score, sheds light on the inherent biases in these models. In response to these findings, we propose a simple yet effective prompt-based solution to alleviate the observed bias in disease prediction with LLMs. This research underscores the importance of fairness in AI, particularly in healthcare applications, and offers a practical approach to enhance the equity of disease prediction models. © 2024 Association for Computational Linguistics.

关键词： Prediction models

来源：评论

学校读者我要写书评

暂无评论

FIRE: A Dataset for Feedback Integration and Refinement Evaluation of Multimodal Models 38

FIRE: A Dataset for Feedback Integration and Refinement Eval...

引用

38th Conference on Neural Information Processing Systems, NeurIPS 2024

作者： Li, Pengxiang Gao, Zhi Zhang, Bofei Yuan, Tao Wu, Yuwei Harandi, Mehrtash Jia, Yunde Zhu, Song-Chun Li, Qing Beijing Key Laboratory of Intelligent Information Technology School of Computer Science & Technology Beijing Institute of Technology China State Key Laboratory of General Artificial Intelligence BIGAI China State Key Laboratory of General Artificial Intelligence Peking University China Department of Electrical and Computer System Engineering Monash University Australia Guangdong Laboratory of Machine Perception and Intelligent Computing Shenzhen MSU-BIT University China Department of Automation Tsinghua University China

Vision language models (VLMs) have achieved impressive progress in diverse applications, becoming a prevalent research direction. In this paper, we build FIRE, a feedback-refinement dataset, consisting of 1.1M multi-turn conversations that are derived from 27 source datasets, empowering VLMs to spontaneously refine their responses based on user feedback across diverse tasks. To scale up the data collection, FIRE is collected in two components: FIRE-100K and FIRE-1M, where FIRE-100K is generated by GPT-4V, and FIRE-1M is freely generated via models trained on FIRE-100K. Then, we build FIRE-Bench, a benchmark to comprehensively evaluate the feedback-refining capability of VLMs, which contains 11K feedback-refinement conversations as the test data, two evaluation settings, and a model to provide feedback for VLMs. We develop the FIRE-LLaVA model by fine-tuning LLaVA on FIRE-100K and FIRE-1M, which shows remarkable feedback-refining capability on FIRE-Bench and outperforms untrained VLMs by 50%, making more efficient user-agent interactions and underscoring the significance of the FIRE dataset. © 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

Style transfer-enabled Sim2Real framework for efficient learning of robotic transesophageal echocardiography using simulation

Style transfer-enabled Sim2Real framework for efficient lear...

引用

2023 International Conference on Biomimetic intelligence and robotics

作者： Li, keyu Mao, Xinyu Ye, Chengwei Li, Ang Xu, Yangxin Meng, Max Q.-H. Department of Electronic Engineering The Chinese University of Hong Kong Hong Kong Shenzhen Key Laboratory of Robotics Perception and Intelligence the Department of Electronic and Electrical Engineering Southern University of Science and Technology Shenzhen518055 China Shenzhen Research Institute The Chinese University of HongKong Shenzhen518057 China

Recently, various machine learning techniques have been proposed to realize automatic ultrasound (US) image analysis for robotic US acquisition tasks. However, obtaining large amounts of real US images for training is usually expensive or even infeasible in some clinical applications, such as transesophageal echocardiography (TEE). An alternative is to build a simulator to generate synthetic US data for training, but the differences between simulated and real US images may result in poor model performance. This work presents a novel Sim2Real framework to learn robotic US image analysis based on simulated data to address the challenges of limited real US data for robotic TEE. A style transfer model is proposed based on unsupervised contrastive learning to convert real US images into the simulation style. Moreover, a task-relevant model is designed to combine CNNs with vision transformers and trained only on the simulated data to generate task-dependent predictions. We demonstrate the effectiveness of our method in an image regression task to predict the probe position based on US images in robotic TEE. Our results show that using only simulated US data and a small amount of unlabelled real data for training, our method can achieve comparable performance to semi-supervised and fully supervised learning methods. Moreover, the effectiveness of our previously proposed CT-based US image simulation method is also indirectly confirmed. © 2023 The Authors. Published by Elsevier B.V.

关键词： robotics

来源：评论

学校读者我要写书评

暂无评论

Reliable observer-based control against sensor failures for fractional order systems 41

Reliable observer-based control against sensor failures for ...

引用

第41届中国控制会议

作者： Bingxin Li Xiangfei Zhao Yaowei Liu Xin Zhao Institute of Robotics and Automatic Information System and the Tianjin Key Laboratory of Intelligent Robotics Nankai University Institute of Intelligence Technology and Robotic Systems Shenzhen Research Institute of Nankai University

ISBN: (数字)9789887581536

ISBN: (纸本)9781665482561

In the paper,the state and sensor failure observer for fractional order systems with order 0 <α <1 and 1 <α<2 is proposed to estimate the system state and sensor failures at the same *** general,unbounded sensor faults will inevitably lead to system ***,it is very necessary to study the reliable controller for fractional order systems against sensor *** the linear matrix inequality concept and the augmented system method,the sensor faults can be in any form,even unbounded.A reliable observer-based controller based on the state and sensor failures estimation is proposed,which can make the system work well regardless of whether the sensor *** α=1,methods proposed in the paper are equivalent to these of the integer order systems,scilicet,our methods can be extended to integer order ***,a simulation example is used to demonstrate the efficiency of the present methods.

关键词： Fractional order systems state and sensor failures linear matrix inequality reliable observer-based controller

来源：评论

学校读者我要写书评

暂无评论

Supermaneuverable Flipping Control and Planning Based on Multi-Rotor Mode of Tilt-Rotor UAVs

Supermaneuverable Flipping Control and Planning Based on Mul...

引用

2024 IEEE International Conference on robotics and Biomimetics, ROBIO 2024

作者： Wang, Hongpeng Zhang, Qinghao Fei, Yue Deng, Kun Liang, Jun Sun, Chuanyu Xu, Li Civil Aviation University of China The Key Laboratory of Civil Aviation Smart Airport Theory and System China College of Artificial Intelligence Nankai University Tianjin300071 China National University of Defense Technology Laboratory of Science and Technology on Integrated Logistics Support Changsha410073 China Institute of Intelligence Technology and Robotic Systems Shenzhen Research Institute Nankai University Shenzhen518083 China China Nuclear Power Technology Research Institute Co. Ltd Shenzhen518000 China

ISBN: (纸本)9781665481090

Maneuverability is a critical factor for UAV s to survive in high-intensity combat scenarios. Traditional UAV s typically operate in a stable motion state to ensure flight safety. However, in highly contested environments, special missions require high mobility while maintaining safety. Tilt-rotor UAV s, which combine the characteristics of fixed-wing and multi-rotor UAVs, can perform extreme maneuvers, such as high angles of attack and post-stall maneuvers, to rapidly change posture and complete tasks like positioning and defense. Therefore, integrating and optimizing safety and maneuverability metrics is necessary for enabling UAV s to achieve extreme maneuverability. In this paper, extreme maneuver planning and control for tilt-rotor UAV s are realized through a method based on third-order Bezier curve planning of body angular velocity. Experimental results demonstrate tilt-rotor UAVs can perform extreme super-maneuverable flips while maintaining overall process control. © 2024 IEEE.

关键词： Maneuverability

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：