检索结果-内蒙古大学图书馆

Adversarial Robustness of MR Image Reconstruction under Realistic Perturbations

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Morshuis, Jan Nikolas Gatidis, Sergios Hein, Matthias Baumgartner, Christian F. Cluster of Excellence Machine Learning University of Tübingen Germany Max-Planck Institute for Intelligent Systems Germany

Deep learning (DL) methods have shown promising results for solving ill-posed inverse problems such as MR image reconstruction from undersampled k-space data. However, these approaches currently have no guarantees for reconstruction quality and the reliability of such algorithms is only poorly understood. Adversarial attacks offer a valuable tool to understand possible failure modes and worst case performance of DL-based reconstruction algorithms. In this paper we describe adversarial attacks on multi-coil k-space measurements and evaluate them on the recently proposed E2E-VarNet and a simpler UNet-based model. In contrast to prior work, the attacks are targeted to specifically alter diagnostically relevant regions. Using two realistic attack models (adversarial k-space noise and adversarial rotations) we are able to show that current state-of-the-art DL-based reconstruction algorithms are indeed sensitive to such perturbations to a degree where relevant diagnostic information may be lost. Surprisingly, in our experiments the UNet and the more sophisticated E2E-VarNet were similarly sensitive to such attacks. Our findings add further to the evidence that caution must be exercised as DL-based methods move closer to clinical practice. © 2022, CC BY.

关键词： Image reconstruction

Graph learning by Dynamic Sampling

学校读者我要写书评

暂无评论

Graph Learning by Dynamic Sampling

International Joint Conference on Neural Networks (IJCNN)

作者： Luca Hermes Aleksei Liuliakov Malte Schilling Machine Learning Group Bielefeld University Germany Autonomous Intelligent Systems Group University of Münster Germany

Graph neural networks based on message-passing rely on the principle of neighborhood aggregation which has shown to work well for many graph tasks. In other cases these approaches appear insufficient, for example, when graphs are heterophilic. In such cases, it can help to modulate the aggregation method depending on the characteristic of the current neighborhood. Furthermore, when considering higher-order relations, heterophilic settings become even more important. In this work, we investigate a sparse version of message-passing that allows selective neighbor integration and aims for learning to identify most salient nodes that are then integrated over. In our approach, information on individual nodes is encoded by generating distinct walks. Because these walks follow distinct trajectories, the higher-order neighborhood grows only linearly which mitigates information bottlenecks. Overall, we aim to find the most salient substructures by deploying a learnable sampling strategy. We validate our method on commonly used graph benchmarks and show the effectiveness especially in heterophilic graphs. We finally discuss possible extensions to the framework.

关键词：

Deep Visual Heuristics: learning Feasibility of Mixed-Integer Programs for Manipulation Planning

学校读者我要写书评

暂无评论

Deep Visual Heuristics: Learning Feasibility of Mixed-Intege...

IEEE International Conference on Robotics and Automation (ICRA)

作者： Danny Driess Ozgur Oguz Jung-Su Ha Marc Toussaint Machine Learning and Robotics Lab University of Stuttgart Germany Max Planck Institute for Intelligent Systems Stuttgart Germany

ISBN: (数字)9781728173955

ISBN: (纸本)9781728173962

In this paper, we propose a deep neural network that predicts the feasibility of a mixed-integer program from visual input for robot manipulation planning. Integrating learning into task and motion planning is challenging, since it is unclear how the scene and goals can be encoded as input to the learning algorithm in a way that enables to generalize over a variety of tasks in environments with changing numbers of objects and goals. To achieve this, we propose to encode the scene and the target object directly in the image *** experiments show that our proposed network generalizes to scenes with multiple objects, although during training only two objects are present at the same time. By using the learned network as a heuristic to guide the search over the discrete variables of the mixed-integer program, the number of optimization problems that have to be solved to find a feasible solution or to detect infeasibility can greatly be reduced.

关键词： Planning Task analysis Robot sensing systems Neural networks Grasping Search problems

Causal Consistency of Structural Equation Models

学校读者我要写书评

暂无评论

arXiv 2017年

作者： Rubenstein, Paul K. Weichwald, Sebastian Bongers, Stephan Mooij, Joris M. Janzing, Dominik Grosse-Wentrup, Moritz Schölkopf, Bernhard Empirical Inference Mpi for Intelligent Systems Machine Learning Group University of Cambridge Max Planck Eth Center for Learning Systems 4Informatics Institute University of Amsterdam

Complex systems can be modelled at various levels of detail. Ideally, causal models of the same system should be consistent with one another in the sense that they agree in their predictions of the effects of interventions. We formalise this notion of consistency in the case of Structural Equation Models (SEMs) by introducing exact transformations between SEMs. This provides a general language to consider, for instance, the different levels of description in the following three scenarios: (a) models with large numbers of variables versus models in which the 'irrelevant' or unobservable variables have been marginalised out;(b) micro-level models versus macro-level models in which the macrovariables are aggregate features of the microvariables;(c) dynamical time series models versus models of their stationary behaviour. Our analysis stresses the importance of well specified interventions in the causal modelling process and sheds light on the interpretation of cyclic SEMs. Copyright © 2017, The Authors. All rights reserved.

关键词：

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

学校读者我要写书评

暂无评论

arXiv 2024年

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

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. Copyright © 2024, The Authors. All rights reserved.

关键词： Human robot interaction

SLCF-Net: Sequential LiDAR-Camera Fusion for Semantic Scene Completion using a 3D Recurrent U-Net

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Cao, Helin Behnke, Sven Autonomous Intelligent Systems group Computer Science Institute VI-Intelligent Systems and Robotics Center for Robotics and the Lamarr Institute for Machine Learning and Artificial Intelligence University of Bonn Germany

We introduce SLCF-Net, a novel approach for the Semantic Scene Completion (SSC) task that sequentially fuses LiDAR and camera data. It jointly estimates missing geometry and semantics in a scene from sequences of RGB images and sparse LiDAR measurements. The images are semantically segmented by a pre-trained 2D U-Net and a dense depth prior is estimated from a depth-conditioned pipeline fueled by Depth Anything. To associate the 2D image features with the 3D scene volume, we introduce Gaussian-decay Depth-prior Projection (GDP). This module projects the 2D features into the 3D volume along the line of sight with a Gaussian-decay function, centered around the depth prior. Volumetric semantics is computed by a 3D U-Net. We propagate the hidden 3D U-Net state using the sensor motion and design a novel loss to ensure temporal consistency. We evaluate our approach on the SemanticKITTI dataset and compare it with leading SSC approaches. The SLCF-Net excels in all SSC metrics and shows great temporal consistency. Copyright © 2024, The Authors. All rights reserved.

关键词： Semantics

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

学校读者我要写书评

暂无评论

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

IEEE-RAS International Conference on Humanoid Robots

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

ISBN: (数字)9798350373578

ISBN: (纸本)9798350373585

关键词： Knowledge engineering Service robots Large language models Instruments Humanoid robots Reliability engineering Time measurement Planning Prompt engineering Tuning

Improving the Interpretability of GradCAMs in Deep Classification Networks

学校读者我要写书评

暂无评论

Procedia Computer Science 2022年 200卷 620-628页

作者： Alfred Schöttl University of Applied Sciences Munich Dept. of Electrical Engineering and Information Technology Institute for Applications of Machine Learning and Intelligent Systems (IAMLIS) Munich 80335 Germany

Deep classification networks play an important role as backbone networks in industrial AI applications. These applications are often cost or safety critical; explainability of the AI results is a highly demanded feature. We introduce CAM fostering, a method to improve the explainability of classification nets based on local layers such as convolutional or pooling layers. Several CAM interpretability measures are defined and used as additional loss terms. Even though the method requires second-order derivatives, it is demonstrated that deep nets can be trained on large datasets without frozen parameters. The training parameters can be chosen such that the accuracy degradation remains decent in favor of the CAM interpretability improvement. We conclude by comparing the results of different training parameter configurations.

关键词： GradCAM Interpretability CAM fostering

DiffSSC: Semantic LiDAR Scan Completion using Denoising Diffusion Probabilistic Models

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Cao, Helin Behnke, Sven The Autonomous Intelligent Systems group Computer Science Institute VI – Intelligent Systems and Robotics The Center for Robotics The Lamarr Institute for Machine Learning and Artificial Intelligence University of Bonn Germany

Perception systems play a crucial role in autonomous driving, incorporating multiple sensors and corresponding computer vision algorithms. 3D LiDAR sensors are widely used to capture sparse point clouds of the vehicle’s surroundings. However, such systems struggle to perceive occluded areas and gaps in the scene due to the sparsity of these point clouds and their lack of semantics. To address these challenges, Semantic Scene Completion (SSC) jointly predicts unobserved geometry and semantics in the scene given raw LiDAR measurements, aiming for a more complete scene representation. Building on promising results of diffusion models in image generation and super-resolution tasks, we propose their extension to SSC by implementing the noising and denoising diffusion processes in the point and semantic spaces individually. To control the generation, we employ semantic LiDAR point clouds as conditional input and design local and global regularization losses to stabilize the denoising process. We evaluate our approach on autonomous driving datasets and our approach outperforms the state-of-the-art for SSC. © 2024, CC BY.

关键词： Semantics