检索结果-内蒙古大学图书馆

arXiv 2021年

作者： Eskandar, George Abdelsamad, Mohamed Armanious, Karim Yang, Bin Institute of Signal Processing and System Theory University of Stuttgart Stuttgart Germany

Semantic Image Synthesis (SIS) is a subclass of image-to-image translation where a photorealistic image is synthesized from a segmentation mask. SIS has mostly been addressed as a supervised problem. However, state-of-the-art methods depend on a huge amount of labeled data and cannot be applied in an unpaired setting. On the other hand, generic unpaired image-to-image translation frameworks under-perform in comparison, because they color-code semantic layouts and feed them to traditional convolutional networks, which then learn correspondences in appearance instead of semantic content. In this initial work, we propose a new Unsupervised paradigm for Semantic Image Synthesis (USIS) as a first step towards closing the performance gap between paired and unpaired settings. Notably, the framework deploys a SPADE generator that learns to output images with visually separable semantic classes using a self-supervised segmentation loss. Furthermore, in order to match the color and texture distribution of real images without losing high-frequency information, we propose to use whole image wavelet-based discrimination. We test our methodology on 3 challenging datasets and demonstrate its ability to generate multimodal photorealistic images with an improved quality in the unpaired setting. Copyright © 2021, The Authors. All rights reserved.

关键词： Textures

来源：评论

学校读者我要写书评

暂无评论

Grad-LAM: Visualization of Deep Neural Networks for Unsupervised Learning

Grad-LAM: Visualization of Deep Neural Networks for Unsuperv...

引用

European signal processing Conference (EUSIPCO)

作者： Alexander Bartler Darius Hinderer Bin Yang Institute of Signal Processing and System Theory University of Stuttgart Stuttgart Germany

ISBN: (数字)9789082797053

ISBN: (纸本)9781728150017

Nowadays, the explainability of deep neural networks is an essential part of machine learning. In the last years, many methods were developed to visualize important regions of an input image for the decision of the deep neural network. Since almost all methods are designed for supervised trained models, we propose in this work a visualization technique for unsupervised trained autoencoders called Gradient-weighted Latent Activation Mapping (Grad-LAM). We adapt the idea of Grad-CAM and propose a novel weighting based on the knowledge of the autoencoder's decoder. Our method will help to get insights into the highly nonlinear mapping of an input image to a latent space. We show that the visualization maps of Grad-LAM are meaningful on simple datasets like MNIST and the method is even applicable to real-world datasets like ImageNet.

关键词： Visualization Neural networks Europe Machine learning signal processing Decoding Unsupervised learning

来源：评论

学校读者我要写书评

暂无评论

Semi-supervised Riemannian Dimensionality Reduction and Classification Using a Manifold-based Random Walker Graph

Semi-supervised Riemannian Dimensionality Reduction and Clas...

引用

European signal processing Conference (EUSIPCO)

作者： Faezeh Fallah Felix Wiewel Bin Yang Institute of Signal Processing and System Theory University of Stuttgart Stuttgart Germany

ISBN: (数字)9789082797053

ISBN: (纸本)9781728150017

Efficient classification of manifold-based data demands dimensionality reduction. However, the optimal lower dimension is mostly unknown. Also, supervised classification demands a collection of expert-annotated samples. This collection is tedious, costly, and error prone. Thus, semi-supervised classifications are motivated. In this paper, we propose a principled method to determine the optimal lower dimension and to reduce dimension of manifold-based data for their semi-supervised classification. This method relies on a manifold-based random walker graph and enhances the discriminative power of the classifier in the reduced dimensional space. The reduced dimensional data can be classified by any method or the same graph after adapting edge weights of the graph to them. Thus, the proposed dimensionality reduction is independent of the classifier type. This method is evaluated on segmenting tissues on fat-water (2-channel) magnetic resonance images.

关键词： Dimensionality reduction Image segmentation Image edge detection Magnetic resonance Europe signal processing Covariance matrices

来源：评论

学校读者我要写书评

暂无评论

Entropy-based Sample Selection for Online Continual Learning

Entropy-based Sample Selection for Online Continual Learning

引用

European signal processing Conference (EUSIPCO)

作者： Felix Wiewel Bin Yang Institute of Signal Processing and System Theory University of Stuttgart Stuttgart Germany

ISBN: (数字)9789082797053

ISBN: (纸本)9781728150017

Deep neural networks (DNNs) suffer from catastrophic forgetting, a rapid decrease in performance when trained on a sequence of tasks where only data of the most recent task is available. Most previous research has focused on the case where all data of a task is available simultaneously and boundaries between tasks are known. In this paper, we focus on the online setting where data arrives one-by-one or in small batches ordered by tasks and task boundaries are unknown. Avoiding catastrophic forgetting in such a setting is of great interest since it would allow DNNs to accumulate knowledge without the need to store all previously seen data even if task boundaries are unknown. For this, we propose a novel rehearsal algorithm for online continual learning that is derived from basic concepts of information theory. We demonstrate on commonly used data sets that our method can avoid catastrophic forgetting, achieve competitive results when compared with the current state-of-the-art and even outperform it in most cases.

关键词： Neural networks signal processing algorithms Europe signal processing Entropy Task analysis Information theory

来源：评论

学校读者我要写书评

暂无评论

Condensed composite memory continual learning

arXiv

引用

arXiv 2021年

作者： Wiewel, Felix Yang, Bin Institute of Signal Processing and System Theory University of Stuttgart Stuttgart Germany

Deep Neural Networks (DNNs) suffer from a rapid decrease in performance when trained on a sequence of tasks where only data of the most recent task is available. This phenomenon, known as catastrophic forgetting, prevents DNNs from accumulating knowledge over time. Overcoming catastrophic forgetting and enabling continual learning is of great interest since it would enable the application of DNNs in settings where unrestricted access to all the training data at any time is not always possible, e.g. due to storage limitations or legal issues. While many recently proposed methods for continual learning use some training examples for rehearsal, their performance strongly depends on the number of stored examples. In order to improve performance of rehearsal for continual learning, especially for a small number of stored examples, we propose a novel way of learning a small set of synthetic examples which capture the essence of a complete dataset. Instead of directly learning these synthetic examples, we learn a weighted combination of shared components for each example that enables a significant increase in memory efficiency. We demonstrate the performance of our method on commonly used datasets and compare it to recently proposed related methods and baselines. © 2021, CC BY.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

Blind Source Separation of Radar signals in Time Domain Using Deep Learning

Blind Source Separation of Radar Signals in Time Domain Usin...

引用

International Radar Symposium (IRS)

作者： Sven Hinderer Fraunhofer Institute for High Frequency Physics and Radar Techniques FHR Wachtberg Germany Institute of Signal Processing and System Theory University of Stuttgart Stuttgart Germany

ISBN: (数字)9788395602054

ISBN: (纸本)9781665466301

Identification and further analysis of radar emitters in a contested environment requires detection and separation of incoming signals. If they arrive from the same direction and at similar frequencies, deinterleaving them remains challenging. A solution to overcome this limitation becomes increasingly important with the advancement of emitter capabilities. We propose treating the problem as blind source separation in time domain and apply supervisedly trained neural networks to extract the underlying signals from the received mixture. This allows us to handle highly overlapping and also continuous wave (CW) signals from both radar and communication emitters. We make use of advancements in the field of audio source separation and extend a current state-of-the-art model with the objective of deinterleaving arbitrary radio frequency (RF) signals. Results show, that our approach is capable of separating two unknown waveforms in a given frequency band with a single channel receiver.

关键词： Time-frequency analysis RF signals Neural networks Training data Radar Transformers Data models

来源：评论

学校读者我要写书评

暂无评论

AeGAN: Time-Frequency Speech Denoising via Generative Adversarial Networks

AeGAN: Time-Frequency Speech Denoising via Generative Advers...

引用

European signal processing Conference (EUSIPCO)

作者： Sherif Abdulatif Karim Armanious Karim Guirguis Jayasankar T. Sajeev Bin Yang Institute of Signal Processing and System Theory University of Stuttgart Stuttgart Germany

ISBN: (数字)9789082797053

ISBN: (纸本)9781728150017

Automatic speech recognition (ASR) systems are of vital importance nowadays in commonplace tasks such as speech-to-text processing and language translation. This created the need for an ASR system that can operate in realistic crowded environments. Thus, speech enhancement is a valuable building block in ASR systems and other applications such as hearing aids, smartphones and teleconferencing systems. In this paper, a generative adversarial network (GAN) based framework is investigated for the task of speech enhancement, more specifically speech denoising of audio tracks. A new architecture based on CasNet generator and an additional feature-based loss are incorporated to get realistically denoised speech phonetics. Finally, the proposed framework is shown to outperform other learning and traditional model-based speech enhancement approaches.

关键词： Training Time-frequency analysis Noise reduction Speech enhancement Generative adversarial networks Generators Task analysis

来源：评论

学校读者我要写书评

暂无评论

Indoor Positioning based on Active Radar Sensing and Passive Reflectors: Concepts & Initial Results

arXiv

引用

arXiv 2023年

作者： Schlachter, Pascal Yu, Zhibin Iqbal, Naveed Wu, Xiaofeng Hinderer, Sven Yang, Bin Institute of Signal Processing and System Theory University of Stuttgart Pfaffenwaldring 47 Stuttgart70569 Germany Munich Research Center Huawei Technologies Duesseldorf GmbH Riesstraße 25 Munich80992 Germany

To navigate reliably in indoor environments, an industrial autonomous vehicle must know its position. However, current indoor vehicle positioning technologies either lack accuracy, usability or are too expensive. Thus, we propose a novel concept called local reference point assisted active radar positioning, which is able to overcome these drawbacks. It is based on distributing passive retroreflectors in the indoor environment such that each position of the vehicle can be identified by a unique reflection characteristic regarding the reflectors. To observe these characteristics, the autonomous vehicle is equipped with an active radar system. On one hand, this paper presents the basic idea and concept of our new approach towards indoor vehicle positioning and especially focuses on the crucial placement of the reflectors. On the other hand, it also provides a proof of concept by conducting a full system simulation including the placement of the local reference points, the radar-based distance estimation and the comparison of two different positioning methods. It successfully demonstrates the feasibility of our proposed approach. Copyright © 2023, The Authors. All rights reserved.

关键词： Autonomous vehicles

来源：评论

学校读者我要写书评

暂无评论

On-Board Pedestrian Trajectory Prediction Using Behavioral Features

arXiv

引用

arXiv 2022年

作者： Czech, Phillip Braun, Markus Kreßel, Ulrich Yang, Bin Urban Autonomous Driving Department Mercedes-Benz AG Stuttgart Germany Institute of Signal Processing and System Theory University of Stuttgart Stuttgart Germany

This paper presents a novel approach to pedestrian trajectory prediction for on-board camera systems, which utilizes behavioral features of pedestrians that can be inferred from visual observations. Our proposed method, called Behavior-Aware Pedestrian Trajectory Prediction (BA-PTP), processes multiple input modalities, i.e. bounding boxes, body and head orientation of pedestrians as well as their pose, with independent encoding streams. The encodings of each stream are fused using a modality attention mechanism, resulting in a final embedding that is used to predict future bounding boxes in the image. In experiments on two datasets for pedestrian behavior prediction, we demonstrate the benefit of using behavioral features for pedestrian trajectory prediction and evaluate the effectiveness of the proposed encoding strategy. Additionally, we investigate the relevance of different behavioral features on the prediction performance based on an ablation study. Copyright © 2022, The Authors. All rights reserved.

关键词： Forecasting

来源：评论

学校读者我要写书评

暂无评论

On-Board Pedestrian Trajectory Prediction Using Behavioral Features

On-Board Pedestrian Trajectory Prediction Using Behavioral F...

引用

International Conference on Machine Learning and Applications (ICMLA)

作者： Phillip Czech Markus Braun Ulrich Kreßel Bin Yang Urban Autonomous Driving Department Mercedes-Benz AG Stuttgart Germany Institute of Signal Processing and System Theory University of Stuttgart Stuttgart Germany

This paper presents a novel approach to pedestrian trajectory prediction for on-board camera systems, which utilizes behavioral features of pedestrians that can be inferred from visual observations. Our proposed method, called Behavior-Aware Pedestrian Trajectory Prediction (BA-PTP), processes multiple input modalities, i.e. bounding boxes, body and head orientation of pedestrians as well as their pose, with independent encoding streams. The encodings of each stream are fused using a modality attention mechanism, resulting in a final embedding that is used to predict future bounding boxes in the *** experiments on two datasets for pedestrian behavior prediction, we demonstrate the benefit of using behavioral features for pedestrian trajectory prediction and evaluate the effectiveness of the proposed encoding strategy. Additionally, we investigate the relevance of different behavioral features on the prediction performance based on an ablation study.

关键词： Visualization Head Image coding Machine learning Predictive models Streaming media Encoding

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：