检索结果-内蒙古大学图书馆

A Probabilistic Adversarial Autoencoder for Novelty Detection: Leveraging Lightweight Design and Reconstruction Loss

引用

IEEE Access 2025年 13卷 98530-98541页

作者： Muhammad Asad Ihsan Ullah Muhammad Adeel Hafeez Ganesh Sistu Michael G. Madden Machine Learning Research Group School of Computer Science University of Galway Galway Ireland Valeo Vision Systems Tuam Ireland

A novelty detection task involves identifying whether a data point is an outlier, given a training dataset that primarily captures the distribution of inliers. The novel class is usually absent, poorly sampled, or not well defined in the training data. A common technique for anomaly detection at present is to use an adversarial network generator to generate an anomaly score for inputs using the reconstruction loss. However, because this technique uses a competitive training process, it can be unreliable, with its performance being inconsistent during each adversarial training step. This inconsistency arises from changes in the network’s ability to detect anomalies. In this paper, we propose a revised framework for generative probabilistic novelty detection. We use a similar adversarial autoencoder-based framework but with a lightweight deep network, a novel training paradigm, and a probabilistic score to compute the reconstruction loss. Our methodology calculates the probability of whether a sample comes from the inlier distribution or not. The proposed approach can be applied to anomaly and outlier detection in images and videos. We present the results on multiple benchmark datasets, including the challenging UCSD Ped2 dataset for video anomaly detection. Our results illustrate that our proposed method learns the inlier classes and differentiates them from the outlier classes effectively, leading to better results than the baseline and state-of-the-art methods in several benchmark datasets.

关键词： Anomaly detection Training Autoencoders Image reconstruction Videos Data models Training data Probabilistic logic Generators Gaussian noise

来源：评论

学校读者我要写书评

暂无评论

On the Implementation of Baselines and Lightweight Conditional Model Extrapolation (LIMES) Under Class-Prior Shift 4th

On the Implementation of Baselines and Lightweight Condit...

引用

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

作者： Tomaszewska, Paulina Lampert, Christoph H. Warsaw University of Technology Faculty of Mathematics and Information Science Warsaw Poland Machine Learning and Computer Vision Group Klosterneuburg Austria

ISBN: (纸本)9783031407727

This paper focuses on the implementation details of the baseline methods and a recent lightweight conditional model extrapolation algorithm LIMES [5] for streaming data under class-prior shift. LIMES achieves superior performance over the baseline methods, especially concerning the minimum-across-day accuracy, which is important for the users of the system. In this work, the key measures to facilitate reproducibility and enhance the credibility of the results are described. © 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： Lime

来源：评论

学校读者我要写书评

暂无评论

Person Segmentation and Action Classification for Multi-Channel Hemisphere Field of View LiDAR Sensors

Person Segmentation and Action Classification for Multi-Chan...

引用

2025 IEEE/SICE International Symposium on System Integration, SII 2025

作者： Seliunina, Svetlana Otelepko, Artem Memmesheimer, Raphael Behnke, Sven University of Bonn Autonomous Intelligent Systems Group Computer Science Institute VI - Intelligent Systems and Robotics Lamarr Institute for Machine Learning and Artificial Intelligence Center for Robotics Germany

ISBN: (纸本)9798331531614

Robots need to perceive persons in their surroundings for safety and to interact with them. In this paper, we present a person segmentation and action classification approach that operates on 3D scans of hemisphere field of view LiDAR sensors. We recorded a data set with an Ouster OSDome-64 sensor consisting of scenes where persons perform three different actions and annotated it. We propose a method based on a MaskDINO model to detect and segment persons and to recognize their actions from combined spherical projected multi-channel representations of the LiDAR data with an additional positional encoding. Our approach demonstrates good performance for the person segmentation task and further performs well for the estimation of the person action states walking, waving, and sitting. An ablation study provides insights about the individual channel contributions for the person segmentation task. The trained models, code and dataset are made publicly available. © 2025 IEEE.

关键词： Signal encoding

来源：评论

学校读者我要写书评

暂无评论

A Comparison of Prompt Engineering Techniques for Task Planning and Execution in Service Robotics 23

A Comparison of Prompt Engineering Techniques for Task Plann...

引用

23rd IEEE-RAS International Conference on Humanoid Robots, Humanoids 2024

作者： Bode, Jonas Pätzold, Bastian Memmesheimer, Raphael Behnke, Sven Computer Science Institute Vi - Intelligent Systems and Robotics Lamarr Institute for Machine Learning and Artificial Intelligence Center for Robotics University of Bonn Autonomous Intelligent Systems group Germany

ISBN: (纸本)9798350373578

Recent advances in Large Language Models (LLMs) have been instrumental in autonomous robot control and human-robot interaction by leveraging their vast general knowledge and capabilities to understand and reason across a wide range of tasks and scenarios. Previous works have investigated various prompt engineering techniques for improving the performance of LLMs to accomplish tasks, while others have proposed methods that utilize LLMs to plan and execute tasks based on the available functionalities of a given robot platform. In this work, we consider both lines of research by comparing prompt engineering techniques and combinations thereof within the application of high-level task planning and execution in service robotics. We define a diverse set of tasks and a simple set of functionalities in simulation, and measure task completion accuracy and execution time for several state-of-the-art models. We make our code, including all prompts, available at https://***/AIS-Bonn/Prompt-Engineering. © 2024 IEEE.

关键词： Human robot interaction

来源：评论

学校读者我要写书评

暂无评论

Robust Autonomous Vehicle Pursuit Without Expert Steering Labels

引用

IEEE Robotics and Automation Letters 2023年第10期8卷 6595-6602页

作者： Pan, Jiaxin Zhou, Changyao Gladkova, Mariia Khan, Qadeer Cremers, Daniel Technical University of Munich Computer Vision Group Garching85748 Germany Munich Data Science Institute Garching85748 Germany Munich Center for Machine Learning Munchen80333 Germany University of Oxford OxfordOX1 3AZ United Kingdom

In this work, we present a learning method for both lateral and longitudinal motion control of an ego-vehicle for the task of vehicle pursuit. The car being controlled does not have a pre-defined route, rather it reactively adapts to follow a target vehicle while maintaining a safety distance. To train our model, we do not rely on steering labels recorded from an expert driver, but effectively leverage a classical controller as an offline label generation tool. In addition, we account for the errors in the predicted control values, which can lead to a loss of tracking and catastrophic crashes of the controlled vehicle. To this end, we propose an effective data augmentation approach, which allows to train a network that is capable of handling different views of the target vehicle. During the pursuit, the target vehicle is firstly localized using a Convolutional Neural Network. The network takes a single RGB image along with cars' velocities and estimates target vehicle's pose with respect to the ego-vehicle. This information is then fed to a Multi-Layer Perceptron, which regresses the control commands for the ego-vehicle, namely throttle and steering angle. We extensively validate our approach using the CARLA simulator on a wide range of terrains. Our method demonstrates real-time performance, robustness to different scenarios including unseen trajectories and high route completion. © 2016 IEEE.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

Instance Space Analysis and Item Response Theory for Algorithm Testing

Instance Space Analysis and Item Response Theory for Algorit...

引用

2024 Genetic and Evolutionary Computation Conference Companion, GECCO 2024 Companion

作者： Smith-Miles, Kate Muñoz, Mario Andrés Kandanaarachchi, Sevvandi CarltonVIC Australia School of Mathematics and Statistics The University of Melbourne ParkvilleVIC Australia School of Computer and Information Systems The University of Melbourne ParkvilleVIC Australia Statistical Machine Learning Group Data61 CSIRO ClaytonVIC Australia

来源：评论

学校读者我要写书评

暂无评论

Multi-Vehicle Trajectory Prediction at Intersections using State and Intention Information

arXiv

引用

arXiv 2023年

作者： Zhu, Dekai Khan, Qadeer Cremers, Daniel Computer Vision Group CIT Technical University of Munich This work was funded by the Munich Center for Machine Learning Germany

Traditional approaches to prediction of future trajectory of road agents rely on knowing information about their past trajectory. This work rather relies only on having knowledge of the current state and intended direction to make predictions for multiple vehicles at intersections. Furthermore, message passing of this information between the vehicles provides each one of them a more holistic overview of the environment allowing for a more informed prediction. This is done by training a neural network which takes the state and intent of the multiple vehicles to predict their future trajectory. Using the intention as an input allows our approach to be extended to additionally control the multiple vehicles to drive towards desired paths. Experimental results demonstrate the robustness of our approach both in terms of trajectory prediction and vehicle control at intersections. The complete training and evaluation code for this work is available here: https:// ***/Dekai21/Multi_Agent_Intersection. Copyright © 2023, 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

Beyond the Known: Adversarial Autoencoders in Novelty Detection

arXiv

引用

arXiv 2024年

作者： Asad, Muhammad Ullah, Ihsan Sistu, Ganesh Madden, Michael G. Machine Learning Research Group School of Computer Science University of Galway Ireland Insight SFI Research Centre for Data Analytics University of Galway Ireland Valeo Vision Systems Tuam Ireland

In novelty detection, the goal is to decide if a new data point should be categorized as an inlier or an outlier, given a training dataset that primarily captures the inlier distribution. Recent approaches typically use deep encoder and decoder network frameworks to derive a reconstruction error, and employ this error either to determine a novelty score, or as the basis for a one-class classifier. In this research, we use a similar framework but with a lightweight deep network, and we adopt a probabilistic score with reconstruction error. Our methodology calculates the probability of whether the sample comes from the inlier distribution or not. This work makes two key contributions. The first is that we compute the novelty probability by linearizing the manifold that holds the structure of the inlier distribution. This allows us to interpret how the probability is distributed and can be determined in relation to the local coordinates of the manifold tangent space. The second contribution is that we improve the training protocol for the network. Our results indicate that our approach is effective at learning the target class, and it outperforms recent state-of-the-art methods on several benchmark datasets. Copyright © 2024, The Authors. All rights reserved.

关键词： Anomaly detection

来源：评论

学校读者我要写书评

暂无评论

Depth Estimation using Weighted-loss and Transfer learning

arXiv

引用

arXiv 2024年

作者： Hafeez, Muhammad Adeel Madden, Michael G. Sistu, Ganesh Ullah, Ihsan Machine Learning Research Group School of Computer Science University of Galway Ireland Insight SFI Research Centre for Data Analytics University of Galway Ireland Valeo Vision Systems Tuam Ireland

Depth estimation from 2D images is a common computer vision task that has applications in many fields including autonomous vehicles, scene understanding and robotics. The accuracy of a supervised depth estimation method mainly relies on the chosen loss function, the model architecture, quality of data and performance metrics. In this study, we propose a simplified and adaptable approach to improve depth estimation accuracy using transfer learning and an optimized loss function. The optimized loss function is a combination of weighted losses to which enhance robustness and generalization: Mean Absolute Error (MAE), Edge Loss and Structural Similarity Index (SSIM). We use a grid search and a random search method to find optimized weights for the losses, which leads to an improved model. We explore multiple encoder-decoder-based models including DenseNet121, DenseNet169, DenseNet201, and EfficientNet for the supervised depth estimation model on NYU Depth Dataset v2. We observe that the EfficientNet model, pre-trained on ImageNet for classification when used as an encoder, with a simple upsampling decoder, gives the best results in terms of RSME, REL and log10: 0.386, 0.113 and 0.049, respectively. We also perform a qualitative analysis which illustrates that our model produces depth maps that closely resemble ground truth, even in cases where the ground truth is flawed. The results indicate significant improvements in accuracy and robustness, with EfficientNet being the most successful architecture. Copyright © 2024, The Authors. All rights reserved.

关键词： Signal encoding

来源：评论

学校读者我要写书评

暂无评论

MV-Match: Multi-View Matching for Domain-Adaptive Identification of Plant Nutrient Deficiencies

arXiv

引用

arXiv 2024年

作者： Yi, Jinhui Luo, Yanan Deichmann, Marion Schaaf, Gabriel Gall, Juergen Computer Vision Group University of Bonn Bonn Germany Plant Nutrition Group University of Bonn Bonn Germany Lamarr Institute for Machine Learning and Artificial Intelligence Germany

An early, non-invasive, and on-site detection of nutrient deficiencies is critical to enable timely actions to prevent major losses of crops caused by lack of nutrients. While acquiring labeled data is very expensive, collecting images from multiple views of a crop is straightforward. Despite its relevance for practical applications, unsupervised domain adaptation where multiple views are available for the labeled source domain as well as the unlabeled target domain is an unexplored research area. In this work, we thus propose an approach that leverages multiple camera views in the source and target domain for unsupervised domain adaptation. We evaluate the proposed approach on two nutrient deficiency datasets. The proposed method achieves state-of-the-art results on both datasets compared to other unsupervised domain adaptation methods. The dataset and source code are available at https://***/jh-yi/MV-Match. Copyright © 2024, The Authors. All rights reserved.

关键词：

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：