检索结果-内蒙古大学图书馆

On the effects of biased quantum random numbers on the initialization of artificial neural networks

machine learning 2024年第3期113卷 1189-1217页

作者： Heese, Raoul Wolter, Moritz Muecke, Sascha Franken, Lukas Piatkowski, Nico Fraunhofer Ctr Machine Learning Fraunhofer Pl 1 D-67663 Kaiserslautern Germany Fraunhofer Inst Ind Math ITWM Fraunhofer Pl 1 D-67663 Kaiserslautern Germany Fraunhofer Ctr Machine Learning Konrad Adenauer Str D-53757 St Augustin Germany Fraunhofer Inst Algorithms Sci Comp SCAI Schloss Birlinghoven Konrad Adenauer Str D-53757 St Augustin Germany TU Dortmund Univ Artificial Intelligence Grp Otto Hahn Str 12 D-44227 Dortmund Germany Fraunhofer Inst Intelligent Anal & Informat Syst I Schloss Birlinghoven Konrad Adenauer Str D-53757 St Augustin Germany

Recent advances in practical quantum computing have led to a variety of cloud-based quantum computing platforms that allow researchers to evaluate their algorithms on noisy intermediate-scale quantum devices. A common property of quantum computers is that they can exhibit instances of true randomness as opposed to pseudo-randomness obtained from classical systems. Investigating the effects of such true quantum randomness in the context of machine learning is appealing, and recent results vaguely suggest that benefits can indeed be achieved from the use of quantum random numbers. To shed some more light on this topic, we empirically study the effects of hardware-biased quantum random numbers on the initialization of artificial neural network weights in numerical experiments. We find no statistically significant difference in comparison with unbiased quantum random numbers as well as biased and unbiased random numbers from a classical pseudo-random number generator. The quantum random numbers for our experiments are obtained from real quantum hardware.

关键词： Quantum computing Random number generation Neural networks machine learning

来源：评论

学校读者我要写书评

暂无评论

Network transferability of adversarial patches in real-time object detection 2

Network transferability of adversarial patches in real-time ...

引用

Artificial Intelligence for Security and Defence Applications II 2024

作者： Bayer, Jens Becker, Stefan Münch, David Arens, Michael Fraunhofer IOSB Gutleuthausstr. 1 Ettlingen Germany Fraunhofer Center for Machine Learning Germany

ISBN: (纸本)9781510681200

Adversarial patches in computer vision can be used, to fool deep neural networks and manipulate their decision-making process. One of the most prominent examples of adversarial patches are evasion attacks for object detectors. By covering parts of objects of interest, these patches suppress the detections and thus make the target object "invisible" to the object detector. Since these patches are usually optimized on a specific network with a specific train dataset, the transferability across multiple networks and datasets is not given. This paper addresses these issues and investigates the transferability across numerous object detector architectures. Our extensive evaluation across various models on two distinct datasets indicates that patches optimized with larger models provide better network transferability than patches that are optimized with smaller models. © 2024 SPIE.

关键词： Object detection Network architectures

来源：评论

学校读者我要写书评

暂无评论

Wavelet-packets for deepfake image analysis and detection

引用

machine learning 2022年第11期111卷 4295-4327页

作者： Wolter, Moritz Blanke, Felix Heese, Raoul Garcke, Jochen Univ Bonn High Performance Comp & Analyt Lab Bonn Germany Fraunhofer Ctr Machine Learning & SCAI St Augustin Germany Univ Bonn Inst Numer Simulat Bonn Germany Fraunhofer Ctr Machine Learning & ITWM Kaiserslautern Germany

As neural networks become able to generate realistic artificial images, they have the potential to improve movies, music, video games and make the internet an even more creative and inspiring place. Yet, the latest technology potentially enables new digital ways to lie. In response, the need for a diverse and reliable method toolbox arises to identify artificial images and other content. Previous work primarily relies on pixel-space convolutional neural networks or the Fourier transform. To the best of our knowledge, synthesized fake image analysis and detection methods based on a multi-scale wavelet-packet representation, localized in both space and frequency, have been absent thus far. The wavelet transform conserves spatial information to a degree, allowing us to present a new analysis. Comparing the wavelet coefficients of real and fake images allows interpretation. Significant differences are identified. Additionally, this paper proposes to learn a model for the detection of synthetic images based on the wavelet-packet representation of natural and generated images. Our forensic classifiers exhibit competitive or improved performance at small network sizes, as we demonstrate on the Flickr Faces High Quality, Large-scale Celeb Faces Attributes and Large-scale Scene UNderstanding source identification problems. Furthermore, we study the binary Face Forensics++ (ff++) fake-detection problem.

关键词： Signal processing Wavelets Wavelet packets Deepfake detection

来源：评论

学校读者我要写书评

暂无评论

Attention-based Part Assembly for 3D Volumetric Shape Modeling

Attention-based Part Assembly for 3D Volumetric Shape Modeli...

引用

2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2023

作者： Wu, Chengzhi Zheng, Junwei Pfrommer, Julius Beyerer, Jürgen Karlsruhe Institute of Technology Germany Fraunhofer Iosb Germany Fraunhofer Center for Machine Learning Germany

ISBN: (纸本)9798350302493

Modeling a 3D volumetric shape as an assembly of decomposed shape parts is much more challenging, but semantically more valuable than direct reconstruction from a full shape representation. The neural network needs to implicitly learn part relations coherently, which is typically performed by dedicated network layers that can generate transformation matrices for each part. In this paper, we propose a VoxAttention network architecture for attention-based part assembly. We further propose a variant of using channel-wise part attention and show the advantages of this approach. Experimental results show that our method outperforms most state-of-the-art methods for the part relation-aware 3D shape modeling task. © 2023 IEEE.

关键词： Network layers

来源：评论

学校读者我要写书评

暂无评论

An Improved Association Pipeline for Multi-Person Tracking

An Improved Association Pipeline for Multi-Person Tracking

引用

2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2023

作者： Stadler, Daniel Beyerer, Jürgen Karlsruhe Institute of Technology Germany Fraunhofer IOSB Germany Fraunhofer Center for Machine Learning Germany

ISBN: (纸本)9798350302493

The association task of assigning detections to tracks in multi-person tracking has recently been improved by integration of a second matching stage for low-confident detections that are usually discarded in the tracking process. Despite its success, we find that this two stage matching has some weaknesses. For example, high-confident detections are preferred over low-confident detections in any case, even if the low-confident ones are more accurate. Therefore, a Combined Matching (CM) is proposed which considers all possible assignments simultaneously in a single matching stage and thus improves the association accuracy. Moreover, shortcomings of existing motion and appearance distance combinations are identified and a novel Combined Distance (CD) for motion and appearance information is introduced that significantly outperforms previous fusion approaches. Furthermore, we propose an Occlusion Aware Initialization (OAI) which prevents the start of ghost tracks from duplicate detections under occlusion. The effectiveness of our components is shown with extensive ablative experiments and the competitiveness of our tracker is demonstrated on the MOT17 and MOT20 benchmarks, where the current state-of-the-art is notably surpassed. © 2023 IEEE.

关键词： Computer vision

来源：评论

学校读者我要写书评

暂无评论

ReidTrack: Reid-only Multi-target Multi-camera Tracking

ReidTrack: Reid-only Multi-target Multi-camera Tracking

引用

2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2023

作者： Specker, Andreas Beyerer, Jurgen Karlsruhe Institute of Technology Germany Fraunhofer Iosb Germany Fraunhofer Center for Machine Learning Germany

ISBN: (纸本)9798350302493

Multi-target multi-camera tracking of persons in indoor scenarios such as retail stores or warehouses enables efficient placement of products and improvement of working processes. In this work, we propose the ReidTrack framework, which performs the task solely based on peoples' visual appearances. In theory, accurate person re-identification is able to solve the whole task without the need for additional and complex scene models or post-processing steps. ReidTrack is based on clustering appearance embeddings with a mechanism to avoid identity switches caused by detection bounding boxes showing the body parts of multiple individuals. With only a robust person re-identification model and the real-time detector YOLOv8 and without any auxiliary information, such as complex scene models, our approach ranks fourth concerning Track 1 of the 2023 AI City Challenge. © 2023 IEEE.

关键词： Retail stores

来源：评论

学校读者我要写书评

暂无评论

Clark-Park Transformation based Autoencoder for 3-Phase Electrical Signals

Clark-Park Transformation based Autoencoder for 3-Phase Elec...

引用

2023 IEEE PES Innovative Smart Grid Technologies Europe, ISGT EUROPE 2023

作者： Kummerow, André Alramlawi, Mansour Dirbas, Mohammad Nicolai, Steffen Bretschneider, Peter Cognitive Energy Systems Fraunhofer IOSB IOSB-AST Fraunhofer Center for Machine Learning Ilmenau Germany

ISBN: (纸本)9798350396782

During the past decades, significant progress has been made in the field of artificial neural networks to process images (Convolutional Neural Networks), audio signals (Temporal Convolutional Networks), or textual information (Transformers). However, for electrical three-phase signals processing, these network architectures ignore important characteristics and therefore lack of computational efficiency. This can lead to performance problems and limits the application potential of neural networks for a fast and efficient local analysis of three-phase electrical current or voltage waveforms. To address this issue, a novel autoencoder architecture is proposed in this paper, which incorporates Clark-Park transformation to learn the representations of three-phase electrical signals. Using unbalanced and noisy voltage signals, the Clark-Park based autoencoder shows superior performance and computational efficiency compared to recurrent and convolutional benchmark architectures. © 2023 IEEE.

关键词： Autoencoder IEC 61850 Sampled Values Neural Networks Space-Vector Transformation Time Series Analysis

来源：评论

学校读者我要写书评

暂无评论

Companion Paper: Deep Saliency Map Generators for Multispectral Video Classification 4th

Companion Paper: Deep Saliency Map Generators for Multispec...

引用

Fourth International Workshop on Reproducible Research in Pattern Recognition, RRPR 2022

作者： Bayer, Jens Münch, David Arens, Michael Fraunhofer Center for Machine Learning Sankt Augustin Germany Fraunhofer IOSB Gutleuthausstr. 1 Ettlingen76275 Germany

ISBN: (纸本)9783031407727

This is the companion paper for the ICPR 2022 Paper "Deep Saliency Map Generators for Multispectral Video Classification", that investigates the applicability of three saliency map generators on multispectral video input data. In addition to implementation details of modifications for the investigated methods and the used neural network implementations, the influence of the parameters and a more detailed insight in the training and evaluation process is given. © 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： Cell proliferation

来源：评论

学校读者我要写书评

暂无评论

Visual Prompting for Adversarial Robustness 48

Visual Prompting for Adversarial Robustness

引用

48th IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 2023

作者： Chen, Aochuan Lorenz, Peter Yao, Yuguang Chen, Pin-Yu Liu, Sijia Michigan State University United States Fraunhofer Itwm and Fraunhofer Center of Machine Learning Germany Ibm Research United States

ISBN: (纸本)9781728163277

In this work, we leverage visual prompting (VP) to improve adversarial robustness of a fixed, pre-trained model at test time. Compared to conventional adversarial defenses, VP allows us to design universal (i.e., data-agnostic) input prompting templates, which have plug-and-play capabilities at test time to achieve desired model performance without introducing much computation overhead. Although VP has been successfully applied to improving model generalization, it remains elusive whether and how it can be used to defend against adversarial attacks. We investigate this problem and show that the vanilla VP approach is not effective in adversarial defense since a universal input prompt lacks the capacity for robust learning against sample-specific adversarial perturbations. To circumvent it, we propose a new VP method, termed Class-wise Adversarial Visual Prompting (C-AVP), to generate class-wise visual prompts so as to not only leverage the strengths of ensemble prompts but also optimize their interrelations to improve model robustness. Our experiments show that C-AVP outperforms the conventional VP method, with 2.1× standard accuracy gain and 2× robust accuracy gain. Compared to classical test-time defenses, C-AVP also yields a 42× inference time speedup. Code is available at https://***/Phoveran/vp-for-adversarial-robustness. © 2023 IEEE.

关键词： Network security

来源：评论

学校读者我要写书评

暂无评论

OCMCTrack: Online Multi-Target Multi-Camera Tracking with Corrective Matching Cascade

OCMCTrack: Online Multi-Target Multi-Camera Tracking with Co...

引用

IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)

作者： Andreas Specker Fraunhofer IOSB Fraunhofer Center for Machine Learning

ISBN: (数字)9798350365474

ISBN: (纸本)9798350365481

The implementation of multi-target multi-camera tracking systems in indoor environments, including shops and warehouses, facilitates strategic product positioning and the improvement of operational workflows. This paper presents the online multi-target multi-camera tracking framework OCMCTrack, which tracks the 3D positions of people in the world. The proposed framework introduces a novel matching cascade to re-evaluate track assignments dynamically, thus minimizing false positive associations often made by online trackers. Additionally, this work presents three effective methods to enhance the transformation of a person’s position in the image to world coordinates, thereby addressing common inaccuracies in positional reference points. The proposed methodology is able to achieve competitive performance in Track 1 of the 2024 AI City Challenge, demonstrating the effectiveness of the framework.

关键词： Technological innovation Computer vision Three-dimensional displays Annotations Conferences Urban areas Real-time systems

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：