检索结果-内蒙古大学图书馆

11th International Conference on Learning Representations, ICLR 2023

作者： Ji, Haozhe Ke, Pei Hu, Zhipeng Zhang, Rongsheng Huang, Minlie Dept. of Comp. Sci. & Tech. State Key Lab of Intelligent Tech. & Sys. China BNRist Center Tsinghua University Beijing100084 China Fuxi AI Lab NetEase Inc. China

The standard paradigm of neural language generation adopts maximum likelihood estimation (MLE) as the optimizing method. From a distributional view, MLE in fact minimizes the Kullback-Leibler divergence (KLD) between the distribution of the real data and that of the model. However, this approach forces the model to distribute non-zero (sometimes large) probability mass to all training samples regardless of their quality. Moreover, in the attempt to cover the low-probability regions in the data distribution, the model systematically overestimates the probability of corrupted text sequences, which we conjecture is one of the main reasons for text degeneration during autoregressive decoding. To remedy this problem, we leverage the total variation distance (TVD) with its robustness to outliers, and develop practical bounds to apply it to language generation. Then, we introduce the TaiLr objective that balances the tradeoff of estimating TVD. Intuitively, TaiLr downweights real data samples that have low model probabilities with tunable penalization intensity. Experimental results show that our method alleviates the overestimation of degenerated sequences without sacrificing diversity and improves generation quality on a wide range of text generation tasks. © 2023 11th International Conference on Learning Representations, ICLR 2023. All rights reserved.

关键词： Maximum likelihood estimation

来源：评论

学校读者我要写书评

暂无评论

LATEXBLEND: Scaling Multi-concept Customized Generation with Latent Textual Blending

arXiv

引用

arXiv 2025年

作者： Jin, Jian Yu, Zhenbo Shen, Yang Fu, Zhenyong Yang, Jian PCA Lab Key Lab of Intelligent Perception and Systems for High-Dimensional Information Ministry of Education Jiangsu Key Lab of Image and Video Understanding for Social Security School of Computer Science and Engineering Nanjing University of Sci. & Tech. China

Customized text-to-image generation renders user-specified concepts into novel contexts based on textual prompts. Scaling the number of concepts in customized generation meets a broader demand for user creation, whereas existing methods face challenges with generation quality and computational efficiency. In this paper, we propose LATEXBLEND, a novel framework for effectively and efficiently scaling multi-concept customized generation. The core idea of LATEXBLEND is to represent single concepts and blend multiple concepts within a Latent Textual space, which is positioned after the text encoder and a linear projection. LATEXBLEND customizes each concept individually, storing them in a concept bank with a compact representation of latent textual features that captures sufficient concept information to ensure high fidelity. At inference, concepts from the bank can be freely and seamlessly combined in the latent textual space, offering two key merits for multi-concept generation: 1) excellent scalability, and 2) significant reduction of denoising deviation, preserving coherent layouts. Extensive experiments demonstrate that LATEXBLEND can flexibly integrate multiple customized concepts with harmonious structures and high subject fidelity, substantially outperforming baselines in both generation quality and computational efficiency. Project Page. Copyright © 2025, The Authors. All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

SLAM-Based Joint Calibration of Differential RSS Sensor Array and Source Localization 49

SLAM-Based Joint Calibration of Differential RSS Sensor Arra...

引用

49th Annual Conference of the IEEE Industrial Electronics Society, IECON 2023

作者： Fu, Linya Qiao, Xu Huang, Shoudong Mao, Guoqiang Lin, Zhiyun Li, Youfu Kong, He Robotics Institute Uni. of Technology Sydney Sydney Australia Xidian University State Key Laboratory of Integrated Services Networks China City University of Hong Kong Department of Mechanical Engineering China Southern Uni. of Sci. and Tech. Shenzhen Key Laboratory of Control Theory and Intelligent Systems Shenzhen China Southern Uni. of Sci. and Tech. Guangdong Prov. Key Laboratory of Human-Augmentation and Rehabilitation Robotics in Universities Shenzhen China

ISBN: (纸本)9798350331820

Sensor arrays generating differential received signal strength (DRSS) measurements have found many applications in robotics. However, accurate calibration of these sensor arrays remains a challenge. Most existing methods are impractical in that they assume to know signal source positions or certain parameters (i.e., path loss exponent), and try to estimate the others. In this paper, we adopt graph simultaneous localization and mapping (SLAM) as a general framework for jointly estimating the source positions and parameters of the DRSS sensor array. Our contributions are twofold. On the one hand, by using a Fisher information matrix approach, we conduct a systematic observability analysis of the corresponding SLAM setup for the calibration problem. On the other hand, we propose an effective procedure to select the initial value which is fed to Levenberg-Marquardt iterations for further improving optimization accuracy and convergence. Extensive simulation and hardware experiments show that the proposed method renders high-quality calibration results. All the codes and data are publicly available at https://***/SUStech.022/DRSS-sensor-array-calibration. © 2023 IEEE.

关键词： Calibration

来源：评论

学校读者我要写书评

暂无评论

Control of Proton Exchange Membrane Fuel Cell Intake System:A High-Order Fully Actuated System Approach

Control of Proton Exchange Membrane Fuel Cell Intake System:...

引用

第43届中国控制会议

作者： Ganxin Li Fuxing Yao He Kong Yahui Zhang Jinwu Gao Yunfeng Hu Xiaohong Jiao Guilin Wen State Key Laboratory of Crane Technology Yanshan University Shenzhen Key Laboratory of Control Theory and Intelligent Systems Southern Uni.of Sci.and Tech. Department of Control Science and Engineering Jilin University

ISBN: (数字)9789887581581

ISBN: (纸本)9798350366907

The air supply system of the proton exchange membrane fuel cell(PEMFC) has complex characteristics such as multiple inputs and multiple outputs, strong nonlinear coupling, and internal and external disturbances. Controlling the airflow and cathode pressure in coordination is a great challenge. To deal with this challenge, this paper designs a novel strategy based on high-order fully actuated(HOFA) systems theory. First, the fourth-order underactuated system of PEMFC is transformed into an HOFA system, and an extended state observer is designed to estimate unmodeled dynamics and unknown disturbances and then, based on the characteristics of the HOFA system, a parametric control law is designed to control the airflow and cathode pressure in coordination. Finally, the effectiveness of the HOFA system is validated on a PEMFC air supply system test bench,and the results suggest that our designed strategy can realize accurate and coordinated control of the airflow and cathode pressure,outperforming some existing advanced methods.

关键词： Proton exchange membrane fuel cell Air supply control High-order fully actuated system approaches Extended state observer

来源：评论

学校读者我要写书评

暂无评论

TAILORING LANGUAGE GENERATION MODELS UNDER TOTAL VARIATION DISTANCE

arXiv

引用

arXiv 2023年

作者： Ji, Haozhe Ke, Pei Hu, Zhipeng Zhang, Rongsheng Huang, Minlie Dept. of Comp. Sci. & Tech. State Key Lab of Intelligent Tech. & Sys China BNRist Center Tsinghua University Beijing100084 China Fuxi AI Lab NetEase Inc. China

The standard paradigm of neural language generation adopts maximum likelihood estimation (MLE) as the optimizing method. From a distributional view, MLE in fact minimizes the Kullback-Leibler divergence (KLD) between the distribution of the real data and that of the model. However, this approach forces the model to distribute non-zero (sometimes large) probability mass to all training samples regardless of their quality. Moreover, in the attempt to cover the low-probability regions in the data distribution, the model systematically overestimates the probability of corrupted text sequences, which we conjecture is one of the main reasons for text degeneration during autoregressive decoding. To remedy this problem, we leverage the total variation distance (TVD) with its robustness to outliers, and develop practical bounds to apply it to language generation. Then, we introduce the TaiLr1 objective that balances the tradeoff of estimating TVD. Intuitively, TaiLr downweights real data samples that have low model probabilities with tunable penalization intensity. Experimental results show that our method alleviates the overestimation of degenerated sequences without sacrificing diversity and improves generation quality on a wide range of text generation tasks.2 © 2023, CC0.

关键词： Maximum likelihood estimation

来源：评论

学校读者我要写书评

暂无评论

Driving-Video Dehazing with Non-Aligned Regularization for Safety Assistance

Driving-Video Dehazing with Non-Aligned Regularization for S...

引用

Conference on Computer Vision and Pattern Recognition (CVPR)

作者： Junkai Fan Jiangwei Weng Kun Wang Yijun Yang Jianjun Qian Jun Li Jian Yang PCA Lab Nanjing University of Science and Technology China PCA Lab Key Lab of Intelligent Perception and Systems for High-Dimensional Information of Ministry of Education and Jiangsu Key Lab of Image and Video Understanding for Social Security School of Computer Science and Engineering Nanjing University of Sci. & Tech. The Hong Kong University of Science and Technology Guangzhou

ISBN: (数字)9798350353006

ISBN: (纸本)9798350353013

Real driving-video dehazing poses a significant challenge due to the inherent difficulty in acquiring precisely aligned hazy/clear video pairs for effective model training, especially in dynamic driving scenarios with unpredictable weather conditions. In this paper, we propose a pioneering approach that addresses this challenge through a nonaligned regularization strategy. Our core concept involves identifying clear frames that closely match hazy frames, serving as references to supervise a video dehazing network. Our approach comprises two key components: reference matching and video dehazing. Firstly, we introduce a non-aligned reference frame matching module, leveraging an adaptive sliding window to match high-quality reference frames from clear videos. Video dehazing incorporates flow-guided cosine attention sampler and deformable cosine attention fusion modules to enhance spatial multi-frame alignment and fuse their improved information. To validate our approach, we collect a GoProHazy dataset captured effortlessly with GoPro cameras in diverse rural and urban road environments. Extensive experiments demonstrate the superiority of the proposed method over current state-of-the-art methods in the challenging task of real driving-video dehazing. Project page.

关键词： Training Computer vision Fuses Roads Cameras Safety Pattern recognition

来源：评论

学校读者我要写书评

暂无评论

Tri-Perspective view Decomposition for Geometry-Aware Depth Completion

Tri-Perspective view Decomposition for Geometry-Aware Depth ...

引用

Conference on Computer Vision and Pattern Recognition (CVPR)

作者： Zhiqiang Yan Yuankai Lin Kun Wang Yupeng Zheng Yufei Wang Zhenyu Zhang Jun Li Jian Yang PCA Lab Key Lab of Intelligent Perception and Systems for High-Dimensional Information of Ministry of Education and Jiangsu Key Lab of Image and Video Understanding for Social Security School of Computer Science and Engineering Nanjing University of Sci. & Tech. China Huazhong University of Science and Technology Chinese Academy of Sciences Northwestem Poly technical University Nanjing University

ISBN: (数字)9798350353006

ISBN: (纸本)9798350353013

Depth completion is a vital taskfor autonomous driving, as it involves reconstructing the precise 3D geometry of a scene from sparse and noisy depth measurements. How-ever, most existing methods either rely only on 2D depth representations or directly incorporate raw 3D point clouds for compensation, which are still insufficient to capture the fine-grained 3D geometry of the scene. To address this chal-lenge, we introduce Tri-Perspective View Decomposition (TPVD), a novel framework that can explicitly model 3D geometry. In particular, (1) TPVD ingeniously decomposes the original point cloud into three 2D views, one of which corresponds to the sparse depth input. (2) We design TPV Fusion to update the 2D TPV features through recurrent 2D-3D-2D aggregation, where a Distance-Aware Spherical Convolution (DASC) is applied. (3) By adaptively choosing TPVaffinitive neighbors, the newly proposed Geometric Spatial Propagation Network (GSPN) further improves the geometric consistency. As a result, our TPVD outperforms existing methods on KITTI, NYUv2, and SUN RGBD. Fur-thermore, we build a novel depth completion dataset named TOFDC, which is acquired by the time-of-flight (TOF) sen-sor and the color camera on smart phones. Project page.

关键词： Geometry Point cloud compression Solid modeling Three-dimensional displays Laser radar Convolution Pattern recognition

来源：评论

学校读者我要写书评

暂无评论

SLAM-Based Joint Calibration of Differential RSS Sensor Array and Source Localization

SLAM-Based Joint Calibration of Differential RSS Sensor Arra...

引用

Annual Conference of Industrial Electronics Society

作者： Linya Fu Xu Qiao Shoudong Huang Guoqiang Mao Zhiyun Lin Youfu Li He Kong Shenzhen Key Laboratory of Control Theory and Intelligent Systems Southern Uni. of Sci. and Tech. Shenzhen China Robotics Institute Uni. of Technology Sydney Sydney Australia State Key Laboratory of Integrated Services Networks Xidian University China Department of Mechanical Engineering City University of Hong Kong China Guangdong Provincial Key Laboratory of Human-Augmentation and Rehabilitation Robotics in Universities Southern Uni. of Sci. and Tech. Shenzhen China

关键词：

来源：评论

学校读者我要写书评

暂无评论

Edge Computing and Fault Diagnosis of Rotating Machinery Based on MobileNet in Wireless Sensor Networks for Mechanical Vibration

引用

SENSORS 2024年第16期24卷 5156页

作者： Huang, Yi Liang, Shuang Cui, Tingqiong Mu, Xiaojing Luo, Tianhong Wang, Shengxue Wu, Guangyong Chongqing Univ Arts & Sci Sch Intelligent Mfg Engn Chongqing 402160 Peoples R China Chongqing Univ Int R&D Ctr Micronano Systems & New Mat Technol Key Lab Optoelect Technol & Syst Minist Educ Chongqing 400044 Peoples R China Chongqing City Vocat Coll Dept Informat & Intelligent Engn Chongqing 402160 Peoples R China TF Gorbachev Kuzbass State Tech Univ Min Inst Min Ind Digital Transformat Lab 28 Vesennya St Kemerovo 650000 Russia

With the rapid development of the Industrial Internet of Things in rotating machinery, the amount of data sampled by mechanical vibration wireless sensor networks (MvWSNs) has increased significantly, straining bandwidth capacity. Concurrently, the safety requirements for rotating machinery have escalated, necessitating enhanced real-time data processing capabilities. Conventional methods, reliant on experiential approaches, have proven inefficient in meeting these evolving challenges. To this end, a fault detection method for rotating machinery based on mobileNet in MvWSNs is proposed to address these intractable issues. The small and light deep learning model is helpful to realize nearly real-time sensing and fault detection, lightening the communication pressure of MvWSNs. The well-trained deep learning is implanted on the MvWSNs sensor node, an edge computing platform developed via embedded STM32 microcontrollers (STMicroelectronics International NV, Geneva, Switzerland). Data acquisition, data processing, and data classification are all executed on the computing- and energy-constrained sensor node. The experimental results demonstrate that the proposed fault detection method can achieve about 0.99 for the DDS dataset and an accuracy of 0.98 in the MvWSNs sensor node. Furthermore, the final transmission data size is only 0.1% compared to the original data size. It is also a time-saving method that can be accomplished within 135 ms while the raw data will take about 1000 ms to transmit to the monitoring center when there are four sensor nodes in the network. Thus, the proposed edge computing method shows good application prospects in fault detection and control of rotating machinery with high time sensitivity.

关键词： mechanical equipment monitoring wireless sensor networks mobileNet fault diagnosis edge computing

来源：评论

学校读者我要写书评

暂无评论

The minority matters: a diversity-promoting collaborative metric learning algorithm 22

The minority matters: a diversity-promoting collaborative me...

引用

Proceedings of the 36th International Conference on Neural Information Processing systems

作者： Shilong Bao Qianqian Xu Zhiyong Yang Yuan He Xiaochun Cao Qingming Huang State Key Laboratory of Information Security Institute of Information Engineering CAS and School of Cyber Security University of Chinese Academy of Sciences Key Lab. of Intelligent Information Processing Institute of Computing Technology CAS School of Computer Science and Tech. University of Chinese Academy of Sciences Alibaba Group School of Cyber Science and Technology Shenzhen Campus Sun Yat-sen University Key Lab. of Intelligent Information Processing Institute of Computing Technology CAS and School of Computer Science and Tech. University of Chinese Academy of Sciences and Key Laboratory of Big Data Mining and Knowledge Management CAS and Peng Cheng Laboratory

ISBN: (纸本)9781713871088

Collaborative Metric Learning (CML) has recently emerged as a popular method in recommendation systems (RS), closing the gap between metric learning and Collaborative Filtering. Following the convention of RS, existing methods exploit unique user representation in their model design. This paper focuses on a challenging scenario where a user has multiple categories of interests. Under this setting, we argue that the unique user representation might induce preference bias, especially when the item category distribution is imbalanced. To address this issue, we propose a novel method called Diversity-Promoting Collaborative Metric Learning (DPCML), with the hope of considering the commonly ignored minority interest of the user. The key idea behind DPCML is to include a multiple set of representations for each user in the system. Based on this embedding paradigm, user preference toward an item is aggregated from different embeddings by taking the minimum item-user distance among the user embedding set. Furthermore, we observe that the diversity of the embeddings for the same user also plays an essential role in the model. To this end, we propose a Diversity Control Regularization Scheme (DCRS) to accommodate the multi-vector representation strategy better. Theoretically, we show that DPCML could generalize well to unseen test data by tackling the challenge of the annoying operation that comes from the minimum value. Experiments over a range of benchmark datasets speak to the efficacy of DPCML.

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：