检索结果-内蒙古大学图书馆

SSRN 2024年

作者： Li, Zhifei Luo, Xiangyu Zhang, Miao Zhang, Yan Xiao, Kui School of Computer Science and Information Engineering Hubei University Wuhan430062 China School of Cyber Science and Technology Hubei University Wuhan430062 China Key Laboratory of Intelligent Sensing System and Security Hubei University Ministry of Education Wuhan430062 China Hubei Key Laboratory of Big Data Intelligent Analysis and Application Hubei University Wuhan430062 China

Multi-modal entity alignment aims to integrate equivalent entities in diverse multi-modal knowledge graphs. However, previous studies have primarily focused on multi-modal fusion methods without considering the impact of graph structure heterogeneity on entity alignment tasks due to the distinct structural features of different knowledge graphs. Moreover, the multi-modal information that enriches entity representations, including image, textual content, and numerical attributes, frequently incorporates noise due to modal discrepancies. To tackle these challenges, we introduce the Graph Structural Prefix Injection transformer (GSIEA) for multi-modal entity alignment. This novel approach minimizes structural heterogeneity’s impact and optimizes structural data utilization by integrating a structural prefix inject interaction module within the multi-head attention mechanism. Then, we adopt a convolutional enhancement module to extract local features of multi-modal information and complete feature fusion by cross-modal weights. Extensive experiments on two datasets demonstrate that GSIEA outperforms previous baseline models, showcasing an average performance improvement of 3.26% on MRR, with a maximum enhancement of 12.5%. Additionally, the average performance improvement on Hits@1 is 4.96%, with a maximum enhancement of 16.92%. Our code is available at https://***/HubuKG/GSIEA. © 2024, The Authors. All rights reserved.

关键词： Knowledge graph

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

Improve Cross-domain Mixed Sampling with Guidance Training for Adaptive Segmentation

arXiv

引用

arXiv 2024年

作者： Zhou, Wenlve Zhou, Zhiheng Wang, Tianlei Zeng, Delu School of Electronic and Information Engineering South China University of Technology Guangdong Guangzhou510641 China Key Laboratory of Big Data and Intelligent Robot Ministry of Education South China University of Technology Guangzhou510641 China The Department of Intelligent Manufacturing Wuyi University Jiangmen529020 China

Unsupervised Domain Adaptation (UDA) endeavors to adjust models trained on a source domain to perform well on a target domain without requiring additional annotations. In the context of domain adaptive semantic segmentation, which tackles UDA for dense prediction, the goal is to circumvent the need for costly pixel-level annotations. Typically, various prevailing methods baseline rely on constructing intermediate domains via cross-domain mixed sampling techniques to mitigate the performance decline caused by domain gaps. However, such approaches generate synthetic data that diverge from real-world distributions, potentially leading the model astray from the true target distribution. To address this challenge, we propose a novel auxiliary task called Guidance Training. This task facilitates the effective utilization of cross-domain mixed sampling techniques while mitigating distribution shifts from the real world. Specifically, Guidance Training guides the model to extract and reconstruct the target-domain feature distribution from mixed data, followed by decoding the reconstructed target-domain features to make pseudo-label predictions. Importantly, integrating Guidance Training incurs minimal training overhead and imposes no additional inference burden. We demonstrate the efficacy of our approach by integrating it with existing methods, consistently improving performance. The implementation will be available at https://***/Wenlve-Zhou/Guidance-Training. Copyright © 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

Sharing, Teaching and Aligning: Knowledgeable Transfer Learning for Cross-Lingual Machine Reading Comprehension

arXiv

引用

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

UNeLF: Unconstrained Neural Light Field for Self-Supervised Angular Super-Resolution

引用

IEEE Transactions on Circuits and Systems for Video Technology 2025年

作者： Zhao, Mingyuan Sheng, Hao Chen, Rongshan Cong, Ruixuan Cui, Zhenglong Yang, Da Beihang University State Key Laboratory of Virtual Reality Technology and Systems School of Computer Science and Engineering Beijing100191 China Beihang University Data Science and Intelligent Computing Laboratory Hangzhou International Innovation Institute Hangzhou311115 China Macao Polytechnic University Faculty of Applied Sciences 999078 China

Compared to supervised learning methods, self-supervised learning methods address the domain gap problem between light field (LF) datasets collected under varying acquisition conditions, which typically leads to decreased performance when differences exist in the distribution between the training and test sets. However, current self-supervised light field angular super-resolution (LFASR) techniques primarily focus on exploiting discrete spatial-angular features while neglecting continuous LF information. In contrast to previous work, we propose a self-supervised unconstrained neural light field (UNeLF) to continuously represent LF for LFASR. Specifically, any LF can be described as the camera pose for each sub-aperture image (SAI) and the two-plane that captures these SAIs. To describe the former, we introduce a SAIs-dependent pose optimization method to solve the issue that arises from the narrow baseline of most LF data, which hinders robust camera pose estimation. This mechanism reduces the number of trainable camera parameters from a quadratic to a constant scale, thereby alleviating the complexity of joint optimization. For the latter, we propose a novel adaptive two-plane parameterization strategy to determine the two-plane that captures these SAIs, facilitating refocusing. Finally, we jointly optimize the camera parameters, near-far planes and neural light field, efficiently mapping each adaptive two-plane parameterized ray to its correspondence color in a continuous manner. Comprehensive experiments demonstrate that UNeLF achieves faster training and inference with fewer computational resources while exhibiting superior performance on both synthetic and real-world datasets. © 1991-2012 IEEE.

关键词： Self-supervised learning

来源：评论

学校读者我要写书评

暂无评论

Cooperative guidance strategy for multiple hypersonic gliding vehicles system

引用

Chinese Journal of Aeronautics 2020年第3期33卷 990-1005页

作者： Jianglong YU Xiwang DONG Qingdong LI Zhang REN Jinhu LV School of Automation Science and Electrical Engineering Science and Technology on Aircraft Control LaboratoryBeihang UniversityBeijing 100083China Beijing Advanced Innovation Center for Big Data and Brain Computing Beihang UniversityBeijing 100083China Shananxi Key Laboratory of Integrated and Intelligent Navigation Xi’an 710068China

Cooperative guidance strategy for multiple hypersonic gliding vehicles system with flight constraints and cooperative constraints is *** paper mainly cares about the coordination of the entry glide flight phase and driving-down *** from the existing results,both the attack time and the attack angle constraints are considered ***, for the entry glide flight phase, a two-stage method is proposed to achieve the rapid cooperative trajectories planning, where the control signal corridors are designed based on the quasi-equilibrium gliding *** the first stage, the bank angle curve is optimized to achieve the attack angle *** the second stage, the angle of attack curve is optimized to achieve the attack time *** optimized parameters can be obtained by the secant ***, for the driving-down phase, the cooperative terminal guidance law is designed where the terminal attack time and attack angle are *** guidance law is then transformed into the bank angle and angle of attack *** cooperative guidance strategy is summarized as an ***, a numerical simulation example with three hypersonic gliding vehicles is provided for revealing the effectiveness of the acquired strategy and algorithm.

关键词： Attack angle constraints Attack time constraints Cooperative guidance Cooperative path planning Entry guidance Hypersonic vehicles

来源：评论

学校读者我要写书评

暂无评论

Impact of a Compound Droplet on a Solid Surface: The Effect of the Shell on the Core

SSRN

引用

SSRN 2024年

作者： Du, Yuying Dai, Li Qian, Lijuan Zhou, Fang Ma, Yuechao College of Mechanical and Electrical Engineering China Ji liang University Hangzhou310018 China Key Laboratory of intelligent Manufacturing Quality Big Data Tracing and Application of Zhejiang Province China Ji Liang University Hangzhou310018 China

The dynamic behavior of compound droplets impacting a solid surface was studied via experiments over κ (defined as the ratio of the compound droplet shell thickness h to the diameter D0 of compound droplet) ranging from 0 to 0.34, We ranging from 25 to 325 and the viscosity of the shell ranging from 5.92mPa·s to 21.1mPa·s. The spreading diameter ratio, the maximum spreading dynamic contact angle and spreading speed of the core were investigated. Four modalities of the core of compound droplets were observed on the solid surface, including a) core rebound, b) no rebound, c) core rebound splitting, d) core splitting. The results revealed that the thickness of the shell, We, and the viscosity of the shell have a significant effect. The high viscosity oil shell is conducive to its spreading. As the thickness of the oil shell increases, its cushioning effect on the water core also increases. In addition, the boundary between four modalities of the core was identified as a result of the quantified relation between modalities and the shell thickness on the core. Two equations were also proposed for predicting the maximum spreading diameter ratio of the core, which include dimensionless parameters of the compound droplets. © 2024, The Authors. All rights reserved.

关键词： Viscosity

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

Rethinking the visual cues in audio-visual speaker extraction

arXiv

引用

arXiv 2023年

作者： Li, Junjie Ge, Meng Pan, Zexu Cao, Rui Wang, Longbiao Dang, Jianwu Zhang, Shiliang Tianjin Key Laboratory of Cognitive Computing and Application College of Intelligence and Computing Tianjin University Tianjin China Department of Electrical and Computer Engineering National University of Singapore Singapore Institute of Data Science National University of Singapore Singapore Shenzhen Research Institute of Big Data Shenzhen China

The Audio-Visual Speaker Extraction (AVSE) algorithm employs parallel video recording to leverage two visual cues, namely speaker identity and synchronization, to enhance performance compared to audio-only algorithms. However, the visual front-end in AVSE is often derived from a pre-trained model or end-to-end trained, making it unclear which visual cue contributes more to the speaker extraction performance. This raises the question of how to better utilize visual cues. To address this issue, we propose two training strategies that decouple the learning of the two visual cues. Our experimental results demonstrate that both visual cues are useful, with the synchronization cue having a higher impact. We introduce a more explainable model, the Decoupled Audio-Visual Speaker Extraction (DAVSE) model, which leverages both visual cues. Copyright © 2023, The Authors. All rights reserved.

关键词： Extraction

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

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：