Search

Your search keyword '"Dorndorf, A."' showing total 663 results
Start Over Author "Dorndorf, A."
663 results on '"Dorndorf, A."'

1. PartAL: Efficient Partial Active Learning in Multi-Task Visual Settings

Author

Durasov, Nikita, Dorndorf, Nik, and Fua, Pascal

Subjects
Computer Science - Computer Vision and Pattern Recognition
Abstract

Multi-task learning is central to many real-world applications. Unfortunately, obtaining labelled data for all tasks is time-consuming, challenging, and expensive. Active Learning (AL) can be used to reduce this burden. Existing techniques typically involve picking images to be annotated and providing annotations for all tasks. In this paper, we show that it is more effective to select not only the images to be annotated but also a subset of tasks for which to provide annotations at each AL iteration. Furthermore, the annotations that are provided can be used to guess pseudo-labels for the tasks that remain unannotated. We demonstrate the effectiveness of our approach on several popular multi-task datasets.

Published
2022

2. ZigZag: Universal Sampling-free Uncertainty Estimation Through Two-Step Inference

Author

Durasov, Nikita, Dorndorf, Nik, Le, Hieu, and Fua, Pascal

Subjects
Computer Science - Machine Learning, Computer Science - Computer Vision and Pattern Recognition
Abstract

Whereas the ability of deep networks to produce useful predictions has been amply demonstrated, estimating the reliability of these predictions remains challenging. Sampling approaches such as MC-Dropout and Deep Ensembles have emerged as the most popular ones for this purpose. Unfortunately, they require many forward passes at inference time, which slows them down. Sampling-free approaches can be faster but suffer from other drawbacks, such as lower reliability of uncertainty estimates, difficulty of use, and limited applicability to different types of tasks and data. In this work, we introduce a sampling-free approach that is generic and easy to deploy, while producing reliable uncertainty estimates on par with state-of-the-art methods at a significantly lower computational cost. It is predicated on training the network to produce the same output with and without additional information about it. At inference time, when no prior information is given, we use the network's own prediction as the additional information. We then take the distance between the predictions with and without prior information as our uncertainty measure. We demonstrate our approach on several classification and regression tasks. We show that it delivers results on par with those of Ensembles but at a much lower computational cost., Comment: Accepted to Transactions on Machine Learning Research (TMLR), ICML ABBI 2024

Published
2022

14. OPTIMISATION OF THE CALIBRATION PROCESS OF A K-TLS BASED MULTI-SENSOR-SYSTEM BY GENETIC ALGORITHMS

Author

J. Hartmann, I. von Gösseln, N. Schild, A. Dorndorf, J.-A. Paffenholz, and I. Neumann

Subjects
Technology, Engineering (General). Civil engineering (General), TA1-2040, Applied optics. Photonics, TA1501-1820
Abstract

In recent years, the requirements in the industrial production of elongated objects, e.g., aircraft, have been increased. An essential aspect of the production process is the 3D object detection as well as the qualitative assessment of the captured data. On the one hand high accuracy requirements with a 3D standard deviation of σ3D = 1 mm have to be fulfilled, on the other hand an efficient 3D object capturing is needed. In terms of efficiency, kinematic terrestrial laser scanning (k-TLS) has proven its strength in the recent years. It can be seen as an alternative and is even more powerful than to the well established static terrestrial laser scanning (s-TLS). In order to perform a high accurate 3D object capturing with k-TLS, the 3D object capturing of the initial sensor, the (geo-)referencing of the mobile platform, the synchronisation of all sensors and the system calibration, which means the determination of six extrinsic parameters have to be performed with suitable accuracy. Within this contribution we focus on the system calibration. Therefore an approach based on known reference geometries, here planes, is used (Strübing and Neumann, 2013). As a result, the lever arm and boresight angles are determined. Hereby the number as well as the position and orientation of the reference geometries is of importance. Therefore, an optimal arrangement has to be found. Here a sensitive analysis based on uncertainty propagation is used. A selective search of an optimised arrangement is carried out by a genetic algorithm. Within some examples we demonstrate some theoretical aspects and how an optimisation of the reference geometry arrangement can be achieved.

Published
2019
Full Text
View/download PDF

35. Introduction

Author

Dorndorf, Ulrich, Müller, Werner A., editor, Bihn, Martina, editor, and Dorndorf, Ulrich

Published
2002
Full Text
View/download PDF

48. Increasing Feasibility with Dynamic Priority Assignment in Distributed Trajectory Planning for Road Vehicles

Author

Bassam Alrifaee, Georg Dorndorf, and Patrick Scheffe

Abstract

Nonconvex optimal control problems for large-scale networked control systems (NCSs) can be distributed to accelerate computation time. One distribution strategy is priority-based non-cooperative distributed model predictive control. The priorities assigned to agents determine if a feasible solution for all agents exists. This problem has been investigated in the domain of robotics for many years, and has recently been picked up in the domain of road vehicles. We develop a dynamic priority assignment algorithm for road vehicles based on an approach from the domain of robotics. In our algorithm, each vehicle determines its priority in a distributed fashion. The priority of a vehicle increases with the number of potential collisions on its planned path to increase the success of the distributed control problem. We further propose an approach for priority-based non-cooperative distributed model predictive control with dynamic priorities and prove recursive feasibility for the NCS. This paper presents the first evaluation in experiment of the priority assignment algorithm. We compare the algorithm’s performance to dynamic random priorities and to static priorities.

Published
2022
Full Text
View/download PDF

50. Data Warehouses

Author

Dorndorf, Ulrich, Pesch, Erwin, Bernus, Peter, editor, Błażewicz, Jacek, editor, Schmidt, Günter, editor, Shaw, Michael, editor, Kubiak, Wieslaw, editor, Morzy, Tadeusz, editor, and Rusinkiewicz, Marek, editor

Published
2003
Full Text
View/download PDF

Catalog

Books, media, physical & digital resources
See catalog results