Search Results for author: Anton Kummert

Found 8 papers, 1 papers with code

Polynomial Trajectory Predictions for Improved Learning Performance

no code implementations29 Jan 2021 Ido Freeman, Kun Zhao, Anton Kummert

The rising demand for Active Safety systems in automotive applications stresses the need for a reliable short to mid-term trajectory prediction.

Trajectory Prediction

On the Robustness of Active Learning

no code implementations18 Jun 2020 Lukas Hahn, Lutz Roese-Koerner, Peet Cremer, Urs Zimmermann, Ori Maoz, Anton Kummert

Active Learning is concerned with the question of how to identify the most useful samples for a Machine Learning algorithm to be trained with.

Active Learning

Fast Object Classification and Meaningful Data Representation of Segmented Lidar Instances

no code implementations17 Jun 2020 Lukas Hahn, Frederik Hasecke, Anton Kummert

Object detection algorithms for Lidar data have seen numerous publications in recent years, reporting good results on dataset benchmarks oriented towards automotive requirements.

Classification General Classification +3

FLIC: Fast Lidar Image Clustering

no code implementations1 Mar 2020 Frederik Hasecke, Lukas Hahn, Anton Kummert

Lidar sensors are widely used in various applications, ranging from scientific fields over industrial use to integration in consumer products.

Autonomous Driving Image Clustering +2

A Statistical Defense Approach for Detecting Adversarial Examples

no code implementations26 Aug 2019 Alessandro Cennamo, Ido Freeman, Anton Kummert

Then, the signature is projected onto the class-specific statistic vector to infer the input's nature.

Fast and Reliable Architecture Selection for Convolutional Neural Networks

no code implementations6 May 2019 Lukas Hahn, Lutz Roese-Koerner, Klaus Friedrichs, Anton Kummert

The performance of a Convolutional Neural Network (CNN) depends on its hyperparameters, like the number of layers, kernel sizes, or the learning rate for example.

Bayesian Optimisation Neural Architecture Search

EffNet: An Efficient Structure for Convolutional Neural Networks

1 code implementation19 Jan 2018 Ido Freeman, Lutz Roese-Koerner, Anton Kummert

With the ever increasing application of Convolutional Neural Networks to customer products the need emerges for models to efficiently run on embedded, mobile hardware.

Aggregated Channels Network for Real-Time Pedestrian Detection

no code implementations1 Jan 2018 Farzin Ghorban, Javier Marín, Yu Su, Alessandro Colombo, Anton Kummert

Convolutional neural networks (CNNs) have demonstrated their superiority in numerous computer vision tasks, yet their computational cost results prohibitive for many real-time applications such as pedestrian detection which is usually performed on low-consumption hardware.

Pedestrian Detection

Cannot find the paper you are looking for? You can Submit a new open access paper.