检索结果-内蒙古大学图书馆

Semi-supervised riemannian dimensionality reduction and classification using a manifold-based random walker graph 28

学校读者我要写书评

暂无评论

Semi-supervised riemannian dimensionality reduction and clas...

28th European signal processing Conference, EUSIPCO 2020

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

ISBN: (纸本)9789082797053

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. © 2021 European signal processing Conference, EUSIPCO. All rights reserved.

关键词： Magnetic resonance

Grad-LAM: Visualization of deep neural networks for unsupervised learning 28

学校读者我要写书评

暂无评论

Grad-LAM: Visualization of deep neural networks for unsuperv...

28th European signal processing Conference, EUSIPCO 2020

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

ISBN: (纸本)9789082797053

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. © 2021 European signal processing Conference, EUSIPCO. All rights reserved.

关键词： Visualization

Entropy-based sample selection for online continual learning 28

学校读者我要写书评

暂无评论

Entropy-based sample selection for online continual learning

28th European signal processing Conference, EUSIPCO 2020

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

ISBN: (纸本)9789082797053

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. © 2021 European signal processing Conference, EUSIPCO. All rights reserved.

关键词： Deep neural networks

Indoor Positioning based on Active Radar Sensing and Passive Reflectors: Concepts & Initial Results 13

学校读者我要写书评

暂无评论

Indoor Positioning based on Active Radar Sensing and Passive...

13th International Conference on Indoor Positioning and Indoor Navigation - Work-in-Progress Papers, IPIN-WiP 2023

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. © 2023 Copyright for this paper by its authors.

关键词： Autonomous vehicles

Exploring Domain Shift on Radar-Based 3D Object Detection Amidst Diverse Environmental Conditions

学校读者我要写书评

暂无评论

Exploring Domain Shift on Radar-Based 3D Object Detection Am...

International Conference on Intelligent Transportation

作者： Miao Zhang Sherif Abdulatif Benedikt Loesch Marco Altmann Marius Schwarz Bin Yang Robert Bosch GmbH Corporate Research Germany University of Stuttgart Institute of Signal Processing and System Theory Germany

ISBN: (数字)9798331505929

ISBN: (纸本)9798331505936

The rapid evolution of deep learning and its integration with autonomous driving systems have led to substantial advancements in 3D perception using multimodal sensors. Notably, radar sensors show greater robustness compared to cameras and lidar under adverse weather and varying illumination conditions. This study delves into the often-overlooked yet crucial issue of domain shift in 4D radar-based object detection, examining how varying environmental conditions, such as different weather patterns and road types, impact 3D object detection performance. Our findings highlight distinct domain shifts across various weather scenarios, revealing unique dataset sensitivities that underscore the critical role of radar point cloud generation. Additionally, we demonstrate that transitioning between different road types, especially from highways to urban settings, introduces notable domain shifts, emphasizing the necessity for diverse data collection across varied road environments. To the best of our knowledge, this is the first comprehensive analysis of domain shift effects on 4D radar-based object detection. We believe this empirical study contributes to understanding the complex nature of domain shifts in radar data and suggests paths forward for data collection strategy in the face of environmental variability.

关键词： Point cloud compression Meteorological radar Three-dimensional displays Sensitivity Roads Urban areas Object detection Data collection Robustness Meteorology

Class-Aware PillarMix: Can Mixed Sample Data Augmentation Enhance 3D Object Detection with Radar Point Clouds?

学校读者我要写书评

暂无评论

arXiv 2025年

作者： Zhang, Miao Abdulatif, Sherif Loesch, Benedikt Altmann, Marco Yang, Bin Robert Bosch GmbH Corporate Research 71272 Germany University of Stuttgart Institute of Signal Processing and System Theory 70569 Germany

Due to the significant effort required for data collection and annotation in 3D perception tasks, mixed sample data augmentation (MSDA) has been widely studied to generate diverse training samples by mixing existing data. Among these methods, MixUp is a prominent approach that generates new samples by linearly combining two existing ones, using a mix ratio sampled from a β distribution. This simple yet powerful method has inspired numerous variations and applications in 2D and 3D data domains. Recently, many MSDA techniques have been developed for point clouds, but they mainly target LiDAR data, leaving their application to radar point clouds largely unexplored. In this paper, we examine the feasibility of applying existing MSDA methods to radar point clouds and identify several challenges in adapting these techniques. These obstacles stem from the radar’s irregular angular distribution, deviations from a single-sensor polar layout in multi-radar setups, and point sparsity. To address these issues, we propose Class-Aware PillarMix (CAPMix), a novel MSDA approach that applies MixUp at the pillar level in 3D point clouds, guided by class labels. Unlike methods that rely a single mix ratio to the entire sample, CAPMix assigns an independent ratio to each pillar, boosting sample diversity. To account for the density of different classes, we use class-specific distributions: for dense objects (e.g., large vehicles), we skew ratios to favor points from another sample, while for sparse objects (e.g., pedestrians), we sample more points from the original. This class-aware mixing retains critical details and enriches each sample with new information, ultimately generating more diverse training data. Experimental results demonstrate that our method not only significantly boosts performance but also outperforms existing MSDA approaches across two datasets (Bosch Street and K-Radar). We believe that this straightforward yet effective approach will spark further investigation in

关键词： Object detection

Hierarchical Quadratic Random Forest Classifier

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Fallah, Faezeh Institute of Signal Processing and System Theory University of Stuttgart Pfaffenwaldring 47 Stuttgart70569 Germany

In this paper, we proposed a hierarchical quadratic random forest classifier for classifying multiresolution samples extracted from multichannel data. This forest incorporated a penalized multivariate linear discriminant in each of its decision nodes and processed squared features to realize quadratic decision boundaries in the original feature space. The penalized discriminant was based on a multiclass sparse discriminant analysis and the penalization was based on a group Lasso regularizer which was an intermediate between the Lasso and the ridge regularizer. The classification probabilities estimated by this forest and the features learned by its decision nodes could be used standalone or foster graph-based classifiers. © 2023, CC BY-NC-ND.

关键词： Discriminant analysis

Active Inference-Based Optimization of Discriminative Neural Network Classifiers

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Fallah, Faezeh Institute of Signal Processing and System Theory University of Stuttgart Pfaffenwaldring 47 Stuttgart70569 Germany

Commonly used objective functions (losses) for a supervised optimization of discriminative neural network classifiers were either distribution-based or metric-based. The distribution-based losses were mostly based on the cross entropy and fitted the network model to the distribution of the training samples. This could compromise the generalization (predictive performance on unseen samples) or cause classification biases towards the dominant classes of an imbalanced class-sample distribution. The metric-based losses could make the network model independent of any distribution and thus improve its generalization. However, the metrics involved in them were binary classification metrics. This implied to decompose a multiclass classification into a series of one-vs-all classifications and then form the overall loss from an average of the one-vs-all losses. This averaging could naturally lead to a bias towards the dominant classes. Moreover, the metric-based losses could suffer from discrepancies when a class was absent in both the reference (ground truth) labels and the predicted labels. To tackle these issues, recent works have used a combination of the distribution-based and metric-based losses. In this paper, we formulated the optimization of a discriminative neural network classifier within the framework of active inference and showed that the cross entropy-based losses were indeed the variational free energy of a retrospective active inference. Then, we proposed a novel optimization process which not only tackled the unbalancedness of the class-sample distribution of the training samples but also provided a mechanism to tackle errors in the reference (ground truth) labels of the training samples. This was achieved by proposing a novel algorithm to find candidate classification labels of the training samples during the network optimization and a novel objective function for the optimizations. The algorithm could find the candidate labels of the training samples from

关键词： Free energy

Hierarchical Multiresolution Feature- and Prior-based Graphs for Classification

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Fallah, Faezeh Institute of Signal Processing and System Theory University of Stuttgart Pfaffenwaldring 47 Stuttgart70569 Germany

To incorporate spatial (neighborhood) and bidirectional hierarchical relationships as well as features and priors of the samples into their classification, we formulated the classification problem on three variants of multiresolution neighborhood graphs and the graph of a hierarchical conditional random field. Each of these graphs was weighted and undirected and could thus incorporate the spatial or hierarchical relationships in all directions. In addition, each variant of the proposed neighborhood graphs was composed of a spatial feature-based subgraph and an aspatial prior-based subgraph. It expanded on a random walker graph by using novel mechanisms to derive the edge weights of its spatial feature-based subgraph. These mechanisms included implicit and explicit edge detection to enhance detection of weak boundaries between different classes in spatial domain. The implicit edge detection relied on the outlier detection capability of the Tukey’s function and the classification reliabilities of the samples estimated by a hierarchical random forest classifier. Similar mechanism was used to derive the edge weights and thus the energy function of the hierarchical conditional random field. This way, the classification problem boiled down to a system of linear equations and a minimization of the energy function which could be done via fast and efficient techniques. © 2023, CC BY-NC-ND.

关键词： Graphic methods