检索结果-内蒙古大学图书馆

arXiv 2022年

作者： Boutros, Fadi Damer, Naser Kuijper, Arjan Fraunhofer Institute for Computer Graphics Research IGD Darmstadt Germany Department of Computer Science TU Darmstadt Darmstadt Germany

Deep learning-based face recognition models follow the common trend in deep neural networks by utilizing full-precision floating-point networks with high computational costs. Deploying such networks in use-cases constrained by computational requirements is often infeasible due to the large memory required by the full-precision model. Previous compact face recognition approaches proposed to design special compact architectures and train them from scratch using real training data, which may not be available in a real-world scenario due to privacy concerns. We present in this work the QuantFace solution based on low-bit precision format model quantization. QuantFace reduces the required computational cost of the existing face recognition models without the need for designing a particular architecture or accessing real training data. QuantFace introduces privacy-friendly synthetic face data to the quantization process to mitigate potential privacy concerns and issues related to the accessibility to real training data. Through extensive evaluation experiments on seven benchmarks and four network architectures, we demonstrate that QuantFace can successfully reduce the model size up to 5x while maintaining, to a large degree, the verification performance of the full-precision model without accessing real training datasets. All training codes are publicly available 1 © 2022, CC BY-NC-ND.

关键词： Face recognition

来源：评论

学校读者我要写书评

暂无评论

Towards Explaining Demographic Bias through the Eyes of Face Recognition Models

Towards Explaining Demographic Bias through the Eyes of Face...

引用

IEEE International Joint Conference on Biometrics (IJCB)

作者： Biying Fu Naser Damer Fraunhofer Institute for Computer Graphics Research IGD Darmstadt Germany Department of Computer Science TU Darmstadt Darmstadt Germany

ISBN: (纸本)9781665463959

Biases inherent in both data and algorithms make the fairness of widespread machine learning (ML)-based decision-making systems less than optimal. To improve the trustfulness of such ML decision systems, it is crucial to be aware of the inherent biases in these solutions and to make them more transparent to the public and developers. In this work, we aim at providing a set of explainability tool that analyse the difference in the face recognition models' behaviors when processing different demographic groups. We do that by leveraging higher-order statistical information based on activation maps to build explainability tools that link the FR models' behavior differences to certain facial regions. The experimental results on two datasets and two face recognition models pointed out certain areas of the face where the FR models react differently for certain demographic groups compared to reference groups. The outcome of these analyses interestingly aligns well with the results of studies that analyzed the anthropometric differences and the human judgment differences on the faces of different demographic groups. This is thus the first study that specifically tries to explain the biased behavior of FR models on different demographic groups and link it directly to the spatial facial features. The code is publicly available here 1 1 https://***/fbiying87/***.

关键词： Analytical models Machine learning algorithms Codes Face recognition Decision making Machine learning Behavioral sciences

来源：评论

学校读者我要写书评

暂无评论

Towards Explaining Demographic Bias through the Eyes of Face Recognition Models

arXiv

引用

arXiv 2022年

作者： Fu, Biying Damer, Naser Fraunhofer Institute for Computer Graphics Research IGD Darmstadt Germany Department of Computer Science TU Darmstadt Darmstadt Germany

Biases inherent in both data and algorithms make the fairness of widespread machine learning (ML)-based decision-making systems less than optimal. To improve the trustfulness of such ML decision systems, it is crucial to be aware of the inherent biases in these solutions and to make them more transparent to the public and developers. In this work, we aim at providing a set of explainability tool that analyse the difference in the face recognition models’ behaviors when processing different demographic groups. We do that by leveraging higher-order statistical information based on activation maps to build explainability tools that link the FR models’ behavior differences to certain facial regions. The experimental results on two datasets and two face recognition models pointed out certain areas of the face where the FR models react differently for certain demographic groups compared to reference groups. The outcome of these analyses interestingly aligns well with the results of studies that analyzed the anthropometric differences and the human judgment differences on the faces of different demographic groups. This is thus the first study that specifically tries to explain the biased behavior of FR models on different demographic groups and link it directly to the spatial facial features. The code is publicly available here1 © 2022, CC BY.

关键词： Face recognition

来源：评论

学校读者我要写书评

暂无评论

Unsupervised Face Morphing Attack Detection via Self-paced Anomaly Detection

Unsupervised Face Morphing Attack Detection via Self-paced A...

引用

IEEE International Joint Conference on Biometrics (IJCB)

作者： Meiling Fang Fadi Boutros Naser Damer Fraunhofer Institute for Computer Graphics Research IGD Darmstadt Germany Department of Computer Science TU Darmstadt Darmstadt Germany

ISBN: (纸本)9781665463959

The supervised-learning-based morphing attack detection (MAD) solutions achieve outstanding success in dealing with attacks from known morphing techniques and known data sources. However, given variations in the morphing attacks, the performance of supervised MAD solutions drops significantly due to the insufficient diversity and quantity of the existing MAD datasets. To address this concern, we propose a completely unsupervised MAD solution via self-paced anomaly detection (SPL-MAD) by leveraging the existing large-scale face recognition (FR) datasets and the unsupervised nature of convolutional autoencoders. Using general FR datasets that might contain unintentionally and unlabeled manipulated samples to train an autoencoder can lead to a diverse reconstruction behavior of attack and bona fide samples. We analyze this behavior empirically to provide a solid theoretical ground for designing our unsupervised MAD solution. This also results in proposing to integrate our adapted modified self-paced learning paradigm to enhance the reconstruction error separability between the bona fide and attack samples in a completely unsupervised manner. Our experimental results on a diverse set of MAD evaluation datasets show that the proposed unsupervised SPL-MAD solution outperforms the overall performance of a wide range of supervised MAD solutions and provides higher generalizability on unknown attacks. Training codes and pre-trained models are publicly released 1 1 https://***/meilfang/SPL-MAD.

关键词： Training Convolutional codes Adaptation models Face recognition Soft sensors Training data Solids

来源：评论

学校读者我要写书评

暂无评论

DRT: Detection Refinement for Multiple Object Tracking 32

DRT: Detection Refinement for Multiple Object Tracking

引用

32nd British Machine Vision Conference, BMVC 2021

作者： Wang, Bisheng Fruhwirth-Reisinger, Christian Possegger, Horst Bischof, Horst Cao, Guo School of Computer Science and Engineering Nanjing University of Science and Technology China Christian Doppler Laboratory for Embedded Machine Learning Austria Institute of Computer Graphics and Vision Graz University of Technology Austria

Deep learning methods have led to remarkable progress in multiple object tracking (MOT). However, when tracking in crowded scenes, existing methods still suffer from both inaccurate and missing detections. This paper proposes Detection Refinement for Tracking (DRT) to address these two issues for people tracking. First, we construct an encoder-decoder backbone network with a novel semi-supervised heatmap training procedure, which leverages human heatmaps to obtain a more precise localization of the targets. Second, we integrate a "one patch, multiple predictions" mechanism into DRT which refines the detection results and recovers occluded pedestrians at the same time. Additionally, we leverage a data-driven LSTM-based motion model which can recover lost targets at a negligible computational cost. Compared with strong baseline methods, our DRT achieves significant improvements on publicly available MOT datasets. In addition, DRT generalizes well, i.e. it can be applied to any detector to improve their performance. © 2021. The copyright of this document resides with its authors.

关键词： Object detection

来源：评论

学校读者我要写书评

暂无评论

Unsupervised Face Morphing Attack Detection via Self-paced Anomaly Detection

arXiv

引用

arXiv 2022年

作者： Fang, Meiling Boutros, Fadi Damer, Naser Fraunhofer Institute for Computer Graphics Research IGD Darmstadt Germany Department of Computer Science TU Darmstadt Darmstadt Germany

关键词： Face recognition

来源：评论

学校读者我要写书评

暂无评论

Unsupervised Face Recognition using Unlabeled Synthetic Data

arXiv

引用

arXiv 2022年

作者： Boutros, Fadi Klemt, Marcel Fang, Meiling Kuijper, Arjan Damer, Naser Fraunhofer Institute for Computer Graphics Research IGD Darmstadt Germany Department of Computer Science TU Darmstadt Darmstadt Germany

Over the past years, the main research innovations in face recognition focused on training deep neural networks on large-scale identity-labeled datasets using variations of multi-class classification losses. However, many of these datasets are retreated by their creators due to increased privacy and ethical concerns. Very recently, privacy-friendly synthetic data has been proposed as an alternative to privacy-sensitive authentic data to comply with privacy regulations and to ensure the continuity of face recognition research. In this paper, we propose an unsupervised face recognition model based on unlabeled synthetic data (USynthFace). Our proposed USynthFace learns to maximize the similarity between two augmented images of the same synthetic instance. We enable this by a large set of geometric and color transformations in addition to GAN-based augmentation that contributes to the USynthFace model training. We also conduct numerous empirical studies on different components of our USynthFace. With the proposed set of augmentation operations, we proved the effectiveness of our USynthFace in achieving relatively high recognition accuracies using unlabeled synthetic data. The training code and pretrained model are publicly available under https://***/fdbtrs/Unsupervised-Face-Recognition-using-Unlabeled-Synthetic-Data. © 2022, CC BY-NC-SA.

关键词： Face recognition

来源：评论

学校读者我要写书评

暂无评论

Profit aware Resource Allocation in Fog Computing: A Stackelberg Game Approach

Profit aware Resource Allocation in Fog Computing: A Stackel...

引用

2023 IEEE International Conference on computer, Information, and Telecommunication Systems, CITS 2023

作者： Doad, Akshita Gupta, Nitin Obaidat, Mohammad S. Jadon, Kuldeep Singh Rawat, Piyush Hsiao, Kuie-Fang National Institute of Technology Department of Computer Science and Engineering HP Hamirpur India Distinguished Professor at the King Abdullah Ii School of Information Technology The University of Jordan Amman11942 Jordan School of Computer and Communication Engineering University of Science and Technology Beijing Beijing100083 China The Amity University UP Noida201301 India University of Texas-Permain Basin OdessaTX United States

ISBN: (纸本)9798350336092

Recently, Internet of Things (IoT) based smart systems have led to more latency-sensitive and bandwidth hungry IoT applications. Fog computing as an extension of Cloud computing fulfills those requirements more effectively. However, a key challenge for the fog computing is multiple resources allocation between heterogeneous Data Service Operators (DSOs) and End Users (EUs). The DSOs want to increase their revenues, however, due to lack of efficient resource allocation mechanisms, they often end up compromising Quality of Service (QoS) and violating Service Level Agreements (SLAs). It is very important for them to make a balance among user's expectations, expenses of providers and penalties for not providing services within the deadline. Hence, a profit-aware resource allocation policy using Stackelberg game is proposed in the work where DSO acts as leaders and EU as followers. The DSOs being the leaders, set the prices first, send it to the followers, and then the followers can compute their best demand for resources accordingly. Next, Stackelberg equilibrium for each type of resource is obtained to find the best resource demand strategy for an EU. The simulation results demonstrate the superiority of the proposed algorithm. © 2023 IEEE.

关键词： Resource allocation

来源：评论

学校读者我要写书评

暂无评论

Secure Image Steganography Technique based on Hybrid Transforms and Enhanced AES

Secure Image Steganography Technique based on Hybrid Transfo...

引用

2022 International Conference on Augmented Intelligence and Sustainable Systems, ICAISS 2022

作者： Shaik, Syed Basha Devi, D. Sudha Sujithra, M. Sarika, G. Tripathi, Vikas Kapila, Dhiraj K L University Department of Computer Science and Engineering Vijayawada India Coimbatore Institute of Technology Department of Computing-Data Science Coimbatore India Baselios Mathews II College of Engineering Department of Electronics and Communication Engineering Kerala Sasthamkotta India Graphic Era Deemed to Be University Department of Computer Science and Engineering Uttarakhand Dehradun India Lovely Professional University Department of Computer Science and Engineering Phagwara India

ISBN: (纸本)9781665489621

This, work uses a hybrid technique that combines the Modified Advanced Encryption Standard (MAES) and Elliptic Curve Cryptography to encrypt medical images (ECC). This article describes a modified AES for image encryption. For the global cryptosystem, a co-design approach is employed, with MAES processing on the NIOS ii processor and hardware-accelerated scalar ECC multiplication. The suggested cryptographic system executes in a significantly shorter amount of time, which is a critical consideration for real implementation. This security assessment was effective, and our trials reveal that our proposed technique simplifies and corrects cryptography's essentials. In actuality, the results of the evaluation reveal that the proposed method is efficient, rapid, and secure. © 2022 IEEE.

关键词： Image enhancement

来源：评论

学校读者我要写书评

暂无评论

To the Point: From Dynamic Heatmap Video to Gaze Points 25

To the Point: From Dynamic Heatmap Video to Gaze Points

引用

Proceedings of the 2025 Symposium on Eye Tracking Research and Applications

作者： Beryl Gnanaraj Swetha Manivasagam Jaya Sreevalsan-Nair Graphics-Visualization-Computing Lab International Institute of Information Technology Bangalore Bangalore Karnataka India Department of Computer Science and Engineering PSG College of Technology Coimbatore Tamil Nadu India

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：