检索结果-内蒙古大学图书馆

arXiv 2024年

作者： He, Xilin Hu, Jingyu Lin, Qinliang Luo, Cheng Xie, Weicheng Song, Siyang Khan, Muhammad Haris Shen, Linlin Computer Vision Institute School of Computer Science & Software Engineering Shenzhen University China Shenzhen Institute of Artificial Intelligence and Robotics for Society China Guangdong Provincial Key Laboratory of Intelligent Information Processing China University of Exeter United Kingdom Mohamed bin Zayed University of Artificial Intelligence United Arab Emirates

Domain generalization methods aim to learn transferable knowledge from source domains that can generalize well to unseen target domains. Recent studies show that neural networks frequently suffer from a simplicity-biased learning behavior which leads to over-reliance on specific frequency sets, namely as frequency shortcuts, instead of semantic information, resulting in poor generalization performance. Despite previous data augmentation techniques successfully enhancing generalization performances, they intend to apply more frequency shortcuts, thereby causing hallucinations of generalization improvement. In this paper, we aim to prevent such learning behavior of applying frequency shortcuts from a data-driven perspective. Given the theoretical justification of models’ biased learning behavior on different spatial frequency components, which is based on the dataset frequency properties, we argue that the learning behavior on various frequency components could be manipulated by changing the dataset statistical structure in the Fourier domain. Intuitively, as frequency shortcuts are hidden in the dominant and highly dependent frequencies of dataset structure, dynamically perturbating the over-reliance frequency components could prevent the application of frequency shortcuts. To this end, we propose two effective data augmentation modules designed to collaboratively and adaptively adjust the frequency characteristic of the dataset, aiming to dynamically influence the learning behavior of the model and ultimately serving as a strategy to mitigate shortcut learning. Code is available at AdvFrequency. © 2024, CC BY.

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

Pose Estimation of Moving Vehicles Based on Heuristic Rules for Autonomous Driving

Pose Estimation of Moving Vehicles Based on Heuristic Rules ...

引用

2022 IEEE International Conference on Robotics and Biomimetics, ROBIO 2022

作者： He, Yuesheng Zhang, Wei Yang, Ming The Department of Automation Shanghai Jiao Tong University Shanghai200240 China Key Laboratory of System Control and Information Processing Ministry of Education of China Shanghai200240 China Shanghai Engineering Research Center of Intelligent Control and Management Shanghai200240 China Shenzhen Deeproute.ai Co. Ltd China

ISBN: (纸本)9781665481090

Estimating the pose information on moving vehi-cles is one of the most fundamental functions of autonomous driving for detecting and tracking moving objects. The current methods are often based on the prior information of the point cloud distribution, however, the distribution in the actual scene changes dynamically, and is easy not to meet a priori. This paper proposes a 3D pose estimation method based on heuristic rules. In a single frame point cloud, the edge length and edge visibility are used to heuristically screen the candidate orientations established by the convex hull sampling method. On consecutive frame point clouds, tracking heuristics are employed to obtain smoother orientation estimation results. The experimental results on the KITTI dataset and the data from the actual scene of vehicles show that the proposed method reduces the average object-orientation error and improves the accuracy of estimation effectively. © 2022 IEEE.

关键词： Autonomous vehicles

来源：评论

学校读者我要写书评

暂无评论

Integration of NOMA with Reflecting intelligent Surfaces: A Multi-cell Optimization with SIC Decoding Errors

arXiv

引用

arXiv 2022年

作者： Khan, Wali Ullah Lagunas, Eva Mahmood, Asad Ali, Zain Asif, Muhammad Chatzinotas, Symeon Ottersten, Björn SnT University of Luxembourg Luxembourg Department of Electrical and Computer Engineering University of California Santa Cruz United States Guangdong Key Laboratory of Intelligent Information Processing College of Electronics and Information Engineering Shenzhen Univerisyt Guangdong Shenzhen China

Reflecting intelligent surfaces (RIS) has gained significant attention due to its high energy and spectral efficiency in next-generation wireless networks. By using low-cost passive reflecting elements, RIS can smartly reconfigure the signal propagation to extend the wireless communication coverage. On the other hand, non-orthogonal multiple access (NOMA) has been proven as a key air interface technique for supporting massive connections over limited resources. Utilizing the superposition coding and successive interference cancellation (SIC) techniques, NOMA can multiplex multiple users over the same spectrum and time resources by allocating different power levels. This paper proposes a new optimization scheme in a multi-cell RIS-NOMA network to enhance the spectral efficiency under SIC decoding errors. In particular, the power budget of the base station and the transmit power of NOMA users while the passive beamforming of RIS is simultaneously optimized in each cell. Due to objective function and quality of service constraints, the joint problem is formulated as non-convex, which is very complex and challenging to obtain the optimal global solution. To reduce the complexity and make the problem tractable, we first decouple the original problem into two sub-problems for power allocation and passive beamforming. Then, the efficient solution of each sub-problem is obtained in two-steps. In the first-step of For power allocation sub-problem, we transform it to a convex problem by the inner approximation method and then solve it through a standard convex optimization solver in the second-step. Accordingly, in the first-step of passive beamforming, it is transformed into a standard semi-definite programming problem by successive convex approximation and different of convex programming methods. Then, penalty based method is used to achieve a Rank-1 solution for passive beamforming in second-step. Numerical results demonstrate the benefits of the proposed optimization sche

关键词： Convex optimization

来源：评论

学校读者我要写书评

暂无评论

MFCLIP: Multi-modal Fine-grained CLIP for Generalizable Diffusion Face Forgery Detection

arXiv

引用

arXiv 2024年

作者： Zhang, Yaning Wang, Tianyi Yu, Zitong Gao, Zan Shen, Linlin Chen, Shengyong Jinan250353 China Nanyang Technological University 50 Nanyang Ave Block N 4 639798 Singapore School of Computing and Information Technology Great Bay University Dongguan523000 China National Engineering Laboratory for Big Data System Computing Technology Shenzhen University Shenzhen518060 China Jinan250014 China The Key Laboratory of Computer Vision and System Ministry of Education Tianjin University of Technology Tianjin300384 China Computer Vision Institute College of Computer Science and Software Engineering Shenzhen University Shenzhen518060 China National Engineering Laboratory for Big Data System Computing Technology Shenzhen University Shenzhen China Shenzhen Institute of Artificial Intelligence and Robotics for Society Shenzhen518129 China Guangdong Key Laboratory of Intelligent Information Processing Shenzhen University Shenzhen518060 China

The rapid development of photo-realistic face generation methods has raised significant concerns in society and academia, highlighting the urgent need for robust and generalizable face forgery detection (FFD) techniques. Although existing approaches mainly capture face forgery patterns using image modality, other modalities like fine-grained noises and texts are not fully explored, which limits the generalization capability of the model. In addition, most FFD methods tend to identify facial images generated by GAN, but struggle to detect unseen diffusion-synthesized ones. To address the limitations, we aim to leverage the cutting-edge foundation model, contrastive language-image pre-training (CLIP), to achieve generalizable diffusion face forgery detection (DFFD). In this paper, we propose a novel multi-modal fine-grained CLIP (MFCLIP) model, which mines comprehensive and fine-grained forgery traces across image-noise modalities via language-guided face forgery representation learning, to facilitate the advancement of DFFD. Specifically, we devise a fine-grained language encoder (FLE) that extracts fine global language features from hierarchical text prompts. We design a multi-modal vision encoder (MVE) to capture global image forgery embeddings as well as fine-grained noise forgery patterns extracted from the richest patch, and integrate them to mine general visual forgery traces. Moreover, we build an innovative plug-and-play sample pair attention (SPA) method to emphasize relevant negative pairs and suppress irrelevant ones, allowing cross-modality sample pairs to conduct more flexible alignment. Extensive experiments and visualizations show that our model outperforms the state of the arts on different settings like cross-generator, cross-forgery, and cross-dataset evaluations. Copyright © 2024, The Authors. All rights reserved.

关键词： Alignment

来源：评论

学校读者我要写书评

暂无评论

Short-Term Hybrid Prognostics of Fuel Cells: A Comparative and Improvement Study

SSRN

引用

SSRN 2024年

作者： Sheng, Chuang Fu, Jun Zu, YanMin Deng, ZhongHua Li, Xi School of Artificial Intelligence and Automation Key Laboratory of Image Processing and Intelligent Control Education Ministry Huazhong University of Science and Technology Wuhan430074 China Shenzhen Huazhong University of Science and Technology Research Institute Shenzhen518055 China School of Electronic Information Engineering Jingchu University of Technology Jingmen448000 China

Accurately predicting the performance degradation trend of fuel cells helps take measures in advance and prolong the service life of the stack, which led to the creation of a novel hybrid forecasting approach. The first grey model prediction method based on residual exponential smoothing optimization (ES-R-GM) can capture the voltage deterioration trend. The integration of two different ES techniques, specifically the double ES (ES2) and cubic ES (ES3), is explored to investigate their effect on improving the predictive accuracy of the GM model. The second method of the adaptive network fuzzy inference system (ANFIS) can characterize local nonlinear behaviour. The simulated annealing (SA) algorithm is utilized to optimize ANFIS results under different fuzzy rule selection strategies. The outcomes of the two types of prediction methods mentioned above are combined to create a hybrid prediction using the data fusion method and the moving window technique. Different hybrid methods are evaluated under general conditions and further detailed optimization. The proposed hybrid framework is verified by the data obtained from the experimental platform. Moreover, when applied to consistent public datasets, the hybrid approach maintains its robustness and accuracy compared with other prognostic methods. © 2024, The Authors. All rights reserved.

关键词： Simulated annealing

来源：评论

学校读者我要写书评

暂无评论

Clustering single-cell RNA sequencing data by multi-view latent embedding learning

Clustering single-cell RNA sequencing data by multi-view lat...

引用

Computer information Science and Artificial Intelligence (CISAI), International Conference on

作者： Yilong Lin Guanhua Zou Guangdong Key Laboratory of Intelligent Information Processing Shenzhen Key Laboratory of Media Security College of Electronics and Information Engineering Shenzhen University Shenzhen China

ISBN: (纸本)9781665406932

The advancement of single-cell RNA sequencing (scRNA-seq) technologies have provided a great opportunity for characterizing cell types. Most existing clustering methods are always confused by the inherent noise, high dimensionality and dropout events of scRNA-seq data. In this study, we propose a multi-view latent embed- ding learning method, named Encluster, for clustering scRNA-seq data. Specifically, we first generate multiple imputed results of scRNA-seq data by using existing imputation methods. Then we project these imputed results into a low-dimensional shared cell representation matrix, and learn a cell similarity matrix and a cluster indicator matrix from this representation matrix of cells. Additionally, to make our model more adaptive for different data sets, we apply an adaptive self-weighted learning method to assign different weights to different imputed results. According to the experiment results, Encluster is a better method on cell types identification.

关键词： Learning systems Sequential analysis information science Adaptation models RNA Computational modeling Clustering methods

来源：评论

学校读者我要写书评

暂无评论

Forensicability Assessment of Questioned Images in Recapturing Detection

arXiv

引用

arXiv 2022年

作者： Chen, Changsheng Zhao, Lin Cai, Rizhao Yu, Zitong Huang, Jiwu Kot, Alex C. The Guangdong Key Laboratory of Intelligent Information Processing and Shenzhen Key Laboratory of Media Security National Engineering Laboratory for Big Data System Computing Technology College of Electronics and Information Engineering Shenzhen University Shenzhen China Shenzhen Institute of Artificial Intelligence and Robotics for Society China The Department of Electrical and Electrics Engineering Nanyang Technological University Singapore639798 Singapore

Recapture detection of face and document images is an important forensic task. With deep learning, the performances of face anti-spoofing (FAS) and recaptured document detection have been improved significantly. However, the performances are not yet satisfactory on samples with weak forensic cues. The amount of forensic cues can be quantified to allow a reliable forensic result. In this work, we propose a forensicability assessment network to quantify the forensicability of the questioned samples. The low-forensicability samples are rejected before the actual recapturing detection process to improve the efficiency of recapturing detection systems. We first extract forensicability features related to both image quality assessment and forensic tasks. By exploiting domain knowledge of the forensic application in image quality and forensic features, we define three task-specific forensicability classes and the initialized locations in the feature space. Based on the extracted features and the defined centers, we train the proposed forensic assessment network (FANet) with cross-entropy loss and update the centers with a momentum-based update method. We integrate the trained FANet with practical recapturing detection schemes in face anti-spoofing (FAS) and recaptured document detection tasks. Experimental results show that, for a generic CNN-based FAS scheme, FANet reduces the EERs from 33.75% to 19.23% under ROSE to IDIAP protocol by rejecting samples with the lowest 30% forensicability scores. The performance of FAS schemes is poor in the rejected samples, with EER as high as 56.48%. Similar performances in rejecting low-forensicability samples have been observed for the state-of-the-art approaches in FAS and recaptured document detection tasks. To the best of our knowledge, this is the first work that assesses the forensicability of recaptured document images and improves the system efficiency. Copyright © 2022, The Authors. All rights reserved.

关键词： Image quality

来源：评论

学校读者我要写书评

暂无评论

Vision Language Modeling of Content, Distortion and Appearance for Image Quality Assessment

arXiv

引用

arXiv 2024年

作者： Zhou, Fei Gu, Tianhao Huang, Zhicong Qiu, Guoping College of Electronic and Information Engineering Shenzhen University Shenzhen518060 China Guangdong Provincial Key Laboratory of Intelligent Information Processing Shenzhen518060 China SZU-AFS Joint Innovation Center for Artificial Intelligence Technology Shenzhen518000 China Guangdong-Hong Kong Joint Laboratory for Big Data Imaging and Communication Shenzhen518060 China School of Computer Science The University of Nottingham Ningbo China Zhejiang315100 China School of Computer Science University of Nottingham NottinghamNG8 1BB United Kingdom

The visual quality of an image is confounded by a number of intertwined factors including its semantic content, distortion characteristics and appearance properties such as brightness, contrast, sharpness, and colourfulness. Distilling high level knowledge about all these quality bearing attributes is crucial for developing objective Image Quality Assessment (IQA). While existing solutions have modeled some of these aspects, a comprehensive solution that involves all these important quality related attributes has not yet been developed. In this paper, we present a new blind IQA (BIQA) model termed Self-supervision and Vision-Language supervision Image QUality Evaluator (SLIQUE) that features a joint vision-language and visual contrastive representation learning framework for acquiring high level knowledge about the images semantic contents, distortion characteristics and appearance properties for IQA. For training SLIQUE, we have developed a systematic approach to constructing a first of its kind large image database annotated with all three categories of quality relevant texts. The Text Annotated Distortion, Appearance and Content (TADAC1) database has over 1.6 million images annotated with textual descriptions of their semantic contents, distortion characteristics and appearance properties. The method for constructing TADAC and the database itself will be particularly useful for exploiting vision-language modeling for advanced IQA applications. Extensive experimental results show that SLIQUE has superior performances over state of the art, demonstrating the soundness of its design principle and the effectiveness of its implementation. The link to the TADAC dataset is https://***/documents/tadactextannotated-distortion-appearance-and-content 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

Selective Multi-Scale Learning for Object Detection

arXiv

引用

arXiv 2022年

作者： Chen, Junliang Lu, Weizeng Shen, Linlin Computer Vision Institute School of Computer Science and Software Engineering Shenzhen University China Shenzhen Institute of Artificial Intelligence of Robotics of Society Shenzhen China Guangdong Key Laboratory of Intelligent Information Processing Shenzhen University Shenzhen518060 China

Pyramidal networks are standard methods for multi-scale object detection. Current researches on feature pyramid networks usually adopt layer connections to collect features from certain levels of the feature hierarchy, and do not consider the significant differences among them. We propose a better architecture of feature pyramid networks, named selective multi-scale learning (SMSL), to address this issue. SMSL is efficient and general, which can be integrated in both single-stage and two-stage detectors to boost detection performance, with nearly no extra inference cost. RetinaNet combined with SMSL obtains 1.8% improvement in AP (from 39.1% to 40.9%) on COCO dataset. When integrated with SMSL, two-stage detectors can get around 1.0% improvement in AP. © 2022, CC BY.

关键词： Object detection

来源：评论

学校读者我要写书评

暂无评论

Delving into the Scale Variance Problem in Object Detection

arXiv

引用

arXiv 2022年

作者： Chen, Junliang Zhao, Xiaodong Shen, Linlin Computer Vision Institute School of Computer Science and Software Engineering Shenzhen University China Shenzhen Institute of Artificial Intelligence of Robotics of Society Shenzhen China Guangdong Key Laboratory of Intelligent Information Processing Shenzhen University Shenzhen 518060 China

Object detection has made substantial progress in the last decade, due to the capability of convolution in extracting local context of objects. However, the scales of objects are diverse and current convolution can only process single-scale input. The capability of traditional convolution with a fixed receptive field in dealing with such a scale variance problem, is thus limited. Multi-scale feature representation has been proven to be an effective way to mitigate the scale variance problem. Recent researches mainly adopt partial connection with certain scales, or aggregate features from all scales and focus on the global information across the scales. However, the information across spatial and depth dimensions is ignored. Inspired by this, we propose the multi-scale convolution (MSConv) to handle this problem. Taking into consideration scale, spatial and depth information at the same time, MSConv is able to process multi-scale input more comprehensively. MSConv is effective and computationally efficient, with only a small increase of computational cost. For most of the single-stage object detectors, replacing the traditional convolutions with MSConvs in the detection head can bring more than 2.5% improvement in AP (on COCO 2017 dataset), with only 3% increase of FLOPs. MSConv is also flexible and effective for two-stage object detectors. When extended to the mainstream two-stage object detectors, MSConv can bring up to 3.0% improvement in AP. Our best model under single-scale testing achieves 48.9% AP on COCO 2017 test-dev split, which surpasses many state-of-the-art methods. © 2022, CC BY.

关键词： Object detection

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：