检索结果-内蒙古大学图书馆

arXiv 2023年

作者： Cao, Tingfeng Wang, Chengyu Tan, Chuanqi Huang, Jun Zhu, Jinhui School of Software Engineering South China University of Technology China Alibaba Group China Key Laboratory of Big Data and Intelligent Robot South China University of Technology Ministry of Education China

In cross-lingual language understanding, machine translation is often utilized to enhance the transferability of models across languages, either by translating the training data from the source language to the target, or from the target to the source to aid inference. However, in cross-lingual machine reading comprehension (MRC), it is difficult to perform a deep level of assistance to enhance cross-lingual transfer because of the variation of answer span positions in different languages. In this paper, we propose X-STA, a new approach for cross-lingual MRC. Specifically, we leverage an attentive teacher to subtly transfer the answer spans of the source language to the answer output space of the target. A Gradient-Disentangled Knowledge Sharing technique is proposed as an improved cross-attention block. In addition, we force the model to learn semantic alignments from multiple granularities and calibrate the model outputs with teacher guidance to enhance cross-lingual transferability. Experiments on three multi-lingual MRC datasets show the effectiveness of our method, outperforming state-of-the-art approaches. 1 Copyright © 2023, The Authors. All rights reserved.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

Separate and Integrate Different Level Reasoning for Event Causality Identification

Separate and Integrate Different Level Reasoning for Event C...

引用

International Joint Conference on Neural Networks (IJCNN)

作者： Yuchang Deng Wenti Huang Tingxuan Chen Jun Long School of Software Xinjiang University Urumqi China School of Computer Science and Engineering Hunan University of Science and Technology Changsha China School of Computer Science and Engineering Central South University Changsha China Big Data Institute Central South University Changsha China

ISBN: (数字)9798350359312

ISBN: (纸本)9798350359329

Document-level event causality identification (DECI) aims to discern the causal relationship between two event mentions within a document, which is a more challenging task compared to sentence-level event causality identification. However, the conventional DECI model applies the same method to all pairs of events without considering the distinctions and connections between intra-sentence and inter-sentence event pairs. This paper introduces a novel Separate and Integrate Different Level reasoning model (SIDL) to extract and fuse text features of events. Specifically, we separately encode intra-sentence and inter-sentence event pairs and leverage attention from pre-trained language models to identify the relevant context for aiding in the determination of causality. Additionally, we propose a causal reasoning strategy that leverages intra-sentence causal relationships to assist in the inference of inter-sentence causal relationships. We combine different features of event pairs by discriminating the characters and effects of intra-sentence and inter-sentence reasoning. Experimental results show that our approach achieves superior performance compared to previous models in two benchmarks EventStoryLine and CausalTimeBank.

关键词： Knowledge engineering Correlation Fuses Neural networks Cause effect analysis Benchmark testing Feature extraction

来源：评论

学校读者我要写书评

暂无评论

Sara: Controllable Makeup Transfer with Semantic-Guided Alignment and Region-Adaptive Normalization

SSRN

引用

SSRN 2024年

作者： Zhong, Xiaojing Huang, Xinyi Wu, Zhonghua Lin, Guosheng Wu, Qingyao School of Software Engineering South China University of Technology China School of Computer Science and Engineering Nanyang Technological University Singapore Key Laboratory of Big Data and Intelligent Robot Ministry of Education China Peng Cheng Laboratory China SenseTime Research Hong Kong

Makeup transfer is a process of transferring the makeup style from a reference image to the source image, while preserving the source image's identity. In addition to achieving fine-grained control over the makeup transfer, incorporating semantic alignment into the transformation is crucial, as the poses of the reference and source images are often inconsistent. We propose a novel Semantic-guided Alignment and Region-Adaptive normalization framework (SARA) to effectively transfer makeup styles under misaligned poses, offering flexible control to meet the demands of real-world applications, such as partial transfer, intensity adjustment, and makeup removal. Specifically, SARA comprises three modules: Firstly, we propose a semantic-guided alignment module to explicitly construct dense correspondence between the reference image and the target semantic map, employing unbalanced optimal transport matching to handle semantic region mismatches. Secondly, a region-adaptive normalization module is responsible for dynamically combining the warped style features with shape-independent style codes obtained by region-wise average pooling, mitigating feature loss during the alignment. Lastly, a makeup fusion module progressively fuses the identity features with the makeup styles to render the final output image. Furthermore, we combine optimal transport with histogram matching to generate the pseudo ground truth, which is used to facilitate the transfer in terms of both spatial alignment and color distribution. Experimental results show that our proposed SARA outperforms existing methods on two public datasets. © 2024, The Authors. All rights reserved.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

WMMSE Beamforming for User-Centric Cell-Free Networks with Non-Coherent Joint Transmission

WMMSE Beamforming for User-Centric Cell-Free Networks with N...

引用

IEEE Conference on Global Communications (GLOBECOM)

作者： Xi Wang Xiaotong Zhao Juncheng Wang Qingjiang Shi School of Software Engineering Tongji University Shanghai China Department of Computer Science Hong Kong Baptist University Hong Kong China Shenzhen Research Institute of Big Data Shenzhen China

We consider downlink beamforming design to maximize the weighted sum rate (WSR) in a user-centric cell-free network, where distributed access points (APs) are organized in a cluster to jointly serve each user equipment (UE). This architecture ensures uniform service quality even at the cell edge, but synchronization between APs can be problematic, necessitating the utilization of non-coherent joint transmission (NCJT) that eliminates the need for strict synchronization. Most existing works on beamforming design for NCJT assume that the classic weighted minimum mean square error (WMMSE) approach is not applicable, and design their beamforming algorithms based on the successive convex approximation (SCA) method with high computational complexity. In this work, we for the first time demonstrate the applicability of the WMMSE approach for NCJT in cell-free networks. Based on the unique observations on the structures of the WSR maximization problem for NCJT, we propose an efficient WMMSE based beamforming algorithm. Our proposed algorithm is guaranteed to converge to a stationary point of the WSR maximization problem. Furthermore, our beamforming updates are in closed form with low computational complexity. Simulation results demonstrate substantial performance gain of our proposed algorithm over the current best SCA based alternatives in both computational complexity and convergence time.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Design and Implementation of AMR Robot Based on RGBD, VSLAM and SLAM

Design and Implementation of AMR Robot Based on RGBD, VSLAM ...

引用

9th International Conference on Orange Technology, ICOT 2021

作者： Chen, Che-Wen Lin, Chun-Liang Hsu, Jia-Jiu Tseng, Shih-Pang Wang, Jhing-Fa National Cheng Kung University Department of Electrical Engineering Tainan Taiwan Changzhou College of Information Technology School of Software and Big Data Changzhou China

ISBN: (纸本)9781665478427

In recent years, robots have gradually entered life from the factory. Since robots that can move autonomously can improve the productivity of personnel, mobile robots are even more commonly used. With the advancement of hardware technology, improving the performance of LIDAR and depth cameras and reducing the required cost, robots can be equipped with these devices to make positioning and movement more accurate. This thesis implements an AMR robot on TurtleBot3 Burger by combining 2D LIDAR, RGBD camera and related safety devices. The data of 2D LIDAR is the input of SLAM and path planning, build 2D map and detect whether there are obstacles so that the robot can dodge;RGBD camera is used as the input of VSLAM, build 3D map, landmark database, show trajectory of the robot in 3D space and verify whether the robot has moved to the correct place. In the VSLAM algorithm, object detection and OCR technology are added to extract semantic data from the image. The 3D map and landmark database can provide users with more meaningful information. The landmark database can be used to compare the similarity of SURF features and SSIM with the images obtained when the robot is moving, to verify whether there is movement to the correct place, to improve the accuracy of the robot's movement. The state lights, anti-falling, power detection and warning voice implemented by Arduino and related sensors are used as the safety device of the robot, so that the robot can make higher safety during operation. © 2021 IEEE.

关键词： Cameras

来源：评论

学校读者我要写书评

暂无评论

Scribble-supervised semantic segmentation with prototype-based feature augmentation 24

Scribble-supervised semantic segmentation with prototype-bas...

引用

Proceedings of the 41st International Conference on Machine Learning

作者： Guiyang Chan Pengcheng Zhang Hai Dong Shunhui Ji Bainian Chen Key Laboratory of Water Big Data Technology of Ministry of Water Resources Hohai University Nanjing China and College of Computer Science and Software Engineering Hohai University Nanjing China School of Computing Technologies RMIT University Melbourne Australia

Scribble-supervised semantic segmentation presents a cost-effective training method that utilizes annotations generated through scribbling. It is valued in attaining high performance while minimizing annotation costs, which has made it highly regarded among researchers. Scribble supervision propagates information from labeled pixels to the surrounding unlabeled pixels, enabling semantic segmentation for the entire image. However, existing methods often ignore the features of classified pixels during feature propagation. To address these limitations, this paper proposes a prototype-based feature augmentation method that leverages feature prototypes to augment scribble supervision. Experimental results demonstrate that our approach achieves state-of-the-art performance on the PASCAL VOC 2012 dataset in scribble-supervised semantic segmentation tasks. The code is available at https://***/TranquilChan/PFA.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A Foundation Model for Cell Segmentation from Immunohistochemistry: A Pilot Study

A Foundation Model for Cell Segmentation from Immunohistoche...

引用

IEEE International Symposium on Biomedical Imaging

作者： Wentao Li Xingde Luo Ziqi Yang Xiaofang Jia Zhongyu Li School of Artificial Intelligence University of Chinese Academy of Sciences Beijing China West China Biomedical Big Data Center West China Hospital Sichuan University Chengdu Sichuan China School of Software Engineering Xi'an Jiaotong University Xi'an China

ISBN: (数字)9798331520526

ISBN: (纸本)9798331520533

Cell segmentation plays an important role in the basic research and disease diagnosis of immunohistochemistry (IHC). Although frontiers of large foundation models have been well investigated in H&E stained computational pathology, few works have focused on the diverse and complex analytics of IHC cells, meaning there is currently no foundation model specifically pre-trained on IHC datasets. Furthermore, existing foundation models fail to adequately consider the diversity of contextual priors in IHC images, such as imaging, preparation, and staining methods. Additionally, in downstream segmentation tasks, the popular transformer architecture lacks designs for capturing the subtle structural features of cells. Therefore, in this paper, we establish the first generalizable IHC foundation model (IHCFM), which is pre-trained on a large-scale IHC dataset consisting of 347,226 patches across different hospitals. Meanwhile, to address the diversity of IHC data, we introduce a method to decouple image contextual priors on modeling. Then, we propose the downstream segmentation network, which can effectively capture global and local information in IHC cells. Finally, we evaluate the segmentation performance of the model on a large-scale dataset with 1.2 million manually annotated cells.

关键词： Image segmentation Pathology Foundation models Hospitals Microprocessors Computer architecture Self-supervised learning Transformers Medical diagnosis Immune system

来源：评论

学校读者我要写书评

暂无评论

An Improved Conflict Evidence Management Approach Using Base Belief Function for Uncertain Prior Information Modeling 42

An Improved Conflict Evidence Management Approach Using Base...

引用

42nd Chinese Control Conference, CCC 2023

作者： Tang, Yongchuan Zhou, Yonghao Zhou, Ying Ni, Shuang Huang, Yubo Zhou, Deyun School of Microelectronics Northwestern Polytechnical University Shaanxi Xian710072 China School of Computer Science Northwestern Polytechnical University Shaanxi Xian710072 China School of Electronic Information Northwestern Polytechnical University Shaanxi Xian710072 China School of Big Data and Software Engineering Chongqing University Chongqing401331 China School of Engineering University of Warwick CoventryCV4 7AL United Kingdom

ISBN: (纸本)9789887581543

Due to the complexity in practical environment, there are a variety of interference resulting in inaccurate information which will directly affect the final result of data fusion. In the era of big data, as the number of fusing information sources increases, even if they are consistent, conflicts may arise. However, classical Dempster combination rule in Dempster Shafer evidence theory (D-S theory) cannot solve the problem of conflict data fusion. Therefore, an improved method is proposed for conflict data fusion by assigning a base belief to each piece of evidence. In this paper, the base belief function is used to construct the initial belief degree firstly. Then, the belief entropy is calculated to get the information volume of each evidence. Dempster combination rule is used to get the final result after evidence modification, which can help solve conflict data fusion better. Numerical examples and experiments are used to verity the rationality and effectiveness of the proposed method. © 2023 Technical Committee on Control Theory, Chinese Association of Automation.

关键词： data fusion

来源：评论

学校读者我要写书评

暂无评论

Gradient-Guided Test Case Generation for Image Classification software

Gradient-Guided Test Case Generation for Image Classificatio...

引用

IEEE Annual International Computer software and Applications Conference (COMPSAC)

作者： Shunhui Ji Yunhe Li Hai Dong Mingxuan Xiao Pengcheng Zhang Mengyuan Zhang Key Laboratory of Water Big Data Technology of Ministry of Water Resources Hohai University Nanjing China College of Computer Science and Software Engineering Hohai University Nanjing China School of Computing Technologies RMIT University Melbourne Australia

ISBN: (数字)9798350376968

ISBN: (纸本)9798350376975

The widespread use of deep neural networks (DNNs) in image classification sofwares underlines the importance of the robustness. Researchers have proposed sparse adversarial attack methods for generating test cases, which add pixel-level perturbations to construct the test case to mislead the target model. However, the existing methods have certain limitations, such as high time cost, poor flexibility, and poor quality of the test cases. To address these issues, we propose a gradient-guided test case generation method (GGTM) to evaluate the robustness of image classification software. The method firstly identifies the key region in the image based on the gradient-weighted class activation mapping (Grad-CAM) and the prediction confidence of the target model on the input image. In the key region, it selects a set of pixels as candidate perturbation pixels according to the gradient value and the change of loss function. Then perturbations are added to the candidate perturbation pixels after applying a random dropout strategy to reduce some candidate perturbation pixels which is used to avoid local optimum. For the initially constructed test case which can mislead the target model, after removing redundant and unimportant perturbations, perturbations are re-added to optimize the test case. Experiments show the effectiveness of GGTM, which achieves 100% attack success rate. And the test cases generated by GGTM have the best perturbation sparsity. Furthermore, compared with the baseline method SparseAG which achieves optimal perturbation sparsity among the baseline methods, GGTM significantly improves the efficiency.

关键词： Costs Perturbation methods Artificial neural networks Predictive models software Robustness Image classification

来源：评论

学校读者我要写书评

暂无评论

A Lightweight Convolutional Neural Network with Representation Self-challenge for Fingerprint Liveness Detection

引用

Computers, Materials & Continua 2022年第10期73卷 719-733页

作者： Jie Chen Chengsheng Yuan Chen Cui Zhihua Xia Xingming Sun Thangarajah Akilan School of Computer Science Nanjing University of Information Science and TechnologyNanjing210044China Key Laboratory of Public Security Information Application Based on Big-Data Architecture Ministry of Public SecurityZhejiang Police CollegeHangzhou310053China Jiangsu Yuchi Blockchain Research Institute Nanjing210044China Department of Software Engineering Lakehead UniversityThunder BayON P7B 5E1Canada

Fingerprint identification systems have been widely deployed in many occasions of our daily ***,together with many advantages,they are still vulnerable to the presentation attack(PA)by some counterfeit *** address challenges from PA,fingerprint liveness detection(FLD)technology has been proposed and gradually attracted people’s *** vast majority of the FLD methods directly employ convolutional neural network(CNN),and rarely pay attention to the problem of overparameterization and over-fitting of models,resulting in large calculation force of model deployment and poor model *** at filling this gap,this paper designs a lightweight multi-scale convolutional neural network method,and further proposes a novel hybrid spatial pyramid pooling block to extract abundant features,so that the number of model parameters is greatly reduced,and support multi-scale true/fake fingerprint ***,the representation self-challenge(RSC)method is used to train the model,and the attention mechanism is also adopted for optimization during execution,which alleviates the problem of model over-fitting and enhances generalization of detection ***,experimental results on two publicly benchmarks:LivDet2011 and LivDet2013 sets,show that our method achieves outstanding detection results for blind materials and *** size of the model parameters is only 548 KB,and the average detection error of cross-sensors and cross-materials are 15.22 and 1 respectively,reaching the highest level currently available.

关键词： FLD lightweight multi-scale RSC blind materials

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：