Search Results for author: Matthias Rottmann

Found 41 papers, 17 papers with code

Reducing Texture Bias of Deep Neural Networks via Edge Enhancing Diffusion

no code implementations14 Feb 2024 Edgar Heinert, Matthias Rottmann, Kira Maag, Karsten Kahl

While most of the previous works in the literature focus on the task of image classification, we go beyond this and study the texture bias of CNNs in semantic segmentation.

Adversarial Robustness Domain Generalization +3

Deep Active Learning with Noisy Oracle in Object Detection

no code implementations30 Sep 2023 Marius Schubert, Tobias Riedlinger, Karsten Kahl, Matthias Rottmann

Here, we propose a composite active learning framework including a label review module for deep object detection.

Active Learning Object +2

ResBuilder: Automated Learning of Depth with Residual Structures

no code implementations16 Aug 2023 Julian Burghoff, Matthias Rottmann, Jill von Conta, Sebastian Schoenen, Andreas Witte, Hanno Gottschalk

In this work, we develop a neural architecture search algorithm, termed Resbuilder, that develops ResNet architectures from scratch that achieve high accuracy at moderate computational cost.

Fraud Detection Image Classification +1

Identifying Label Errors in Object Detection Datasets by Loss Inspection

no code implementations13 Mar 2023 Marius Schubert, Tobias Riedlinger, Karsten Kahl, Daniel Kröll, Sebastian Schoenen, Siniša Šegvić, Matthias Rottmann

In this work, we for the first time introduce a benchmark for label error detection methods on object detection datasets as well as a label error detection method and a number of baselines.

Label Error Detection Object +2

Towards Rapid Prototyping and Comparability in Active Learning for Deep Object Detection

no code implementations21 Dec 2022 Tobias Riedlinger, Marius Schubert, Karsten Kahl, Hanno Gottschalk, Matthias Rottmann

Active learning as a paradigm in deep learning is especially important in applications involving intricate perception tasks such as object detection where labels are difficult and expensive to acquire.

Active Learning Object +2

MGiaD: Multigrid in all dimensions. Efficiency and robustness by coarsening in resolution and channel dimensions

no code implementations10 Nov 2022 Antonia van Betteray, Matthias Rottmann, Karsten Kahl

The complexity of the weight count can be seen as a function of the number of channels, the spatial extent of the input and the number of layers of the network.

Image Classification

Semi-supervised domain adaptation with CycleGAN guided by a downstream task loss

no code implementations18 Aug 2022 Annika Mütze, Matthias Rottmann, Hanno Gottschalk

The main contributions of this work are 1) a modular semi-supervised domain adaptation method for semantic segmentation by training a downstream task aware CycleGAN while refraining from adapting the synthetic semantic segmentation expert 2) the demonstration that the method is applicable to complex domain adaptation tasks and 3) a less biased domain gap analysis by using from scratch networks.

Domain Adaptation Image-to-Image Translation +3

Automated Detection of Label Errors in Semantic Segmentation Datasets via Deep Learning and Uncertainty Quantification

1 code implementation13 Jul 2022 Matthias Rottmann, Marco Reese

In this work, we for the first time present a method for detecting label errors in image datasets with semantic segmentation, i. e., pixel-wise class labels.

Benchmarking Label Error Detection +3

False Negative Reduction in Semantic Segmentation under Domain Shift using Depth Estimation

1 code implementation7 Jul 2022 Kira Maag, Matthias Rottmann

In this work, we enhance semantic segmentation predictions using monocular depth estimation to improve segmentation by reducing the occurrence of non-detected objects in presence of domain shift.

Monocular Depth Estimation Segmentation +1

What should AI see? Using the Public's Opinion to Determine the Perception of an AI

no code implementations9 Jun 2022 Robin Chan, Radin Dardashti, Meike Osinski, Matthias Rottmann, Dominik Brüggemann, Cilia Rücker, Peter Schlicht, Fabian Hüger, Nikol Rummel, Hanno Gottschalk

Finally, we include comments from industry leaders in the field of AI safety on the applicability of survey based elements in the design of AI functionalities in automated driving.

Detecting and Learning the Unknown in Semantic Segmentation

no code implementations17 Feb 2022 Robin Chan, Svenja Uhlemeyer, Matthias Rottmann, Hanno Gottschalk

However, this is in contrast to the open world assumption in automated driving that DNNs are deployed to.

Semantic Segmentation

UQGAN: A Unified Model for Uncertainty Quantification of Deep Classifiers trained via Conditional GANs

1 code implementation31 Jan 2022 Philipp Oberdiek, Gernot A. Fink, Matthias Rottmann

We present an approach to quantifying both aleatoric and epistemic uncertainty for deep neural networks in image classification, based on generative adversarial networks (GANs).

Out of Distribution (OOD) Detection Uncertainty Quantification

Towards Unsupervised Open World Semantic Segmentation

1 code implementation4 Jan 2022 Svenja Uhlemeyer, Matthias Rottmann, Hanno Gottschalk

More precisely, the connected components of a predicted semantic segmentation are assessed by a segmentation quality estimate.

Incremental Learning Segmentation +1

Does Redundancy in AI Perception Systems Help to Test for Super-Human Automated Driving Performance?

no code implementations9 Dec 2021 Hanno Gottschalk, Matthias Rottmann, Maida Saltagic

While automated driving is often advertised with better-than-human driving performance, this work reviews that it is nearly impossible to provide direct statistical evidence on the system level that this is actually the case.

False Positive Detection and Prediction Quality Estimation for LiDAR Point Cloud Segmentation

no code implementations29 Oct 2021 Pascal Colling, Matthias Rottmann, Lutz Roese-Koerner, Hanno Gottschalk

We present a novel post-processing tool for semantic segmentation of LiDAR point cloud data, called LidarMetaSeg, which estimates the prediction quality segmentwise.

Point Cloud Segmentation regression +2

Background-Foreground Segmentation for Interior Sensing in Automotive Industry

no code implementations20 Sep 2021 Claudia Drygala, Matthias Rottmann, Hanno Gottschalk, Klaus Friedrichs, Thomas Kurbiel

In this work, we compare different statistical methods from the field of image segmentation to approach the problem of background-foreground segmentation in camera based interior sensing.

Foreground Segmentation Image Segmentation +2

Gradient-Based Quantification of Epistemic Uncertainty for Deep Object Detectors

1 code implementation9 Jul 2021 Tobias Riedlinger, Matthias Rottmann, Marius Schubert, Hanno Gottschalk

The vast majority of uncertainty quantification methods for deep object detectors such as variational inference are based on the network output.

Object object-detection +3

Validation of Simulation-Based Testing: Bypassing Domain Shift with Label-to-Image Synthesis

no code implementations10 Jun 2021 Julia Rosenzweig, Eduardo Brito, Hans-Ulrich Kobialka, Maram Akila, Nico M. Schmidt, Peter Schlicht, Jan David Schneider, Fabian Hüger, Matthias Rottmann, Sebastian Houben, Tim Wirtz

We propose a novel framework consisting of a generative label-to-image synthesis model together with different transferability measures to inspect to what extent we can transfer testing results of semantic segmentation models from synthetic data to equivalent real-life data.

Image Generation Multi-class Classification +2

SegmentMeIfYouCan: A Benchmark for Anomaly Segmentation

2 code implementations30 Apr 2021 Robin Chan, Krzysztof Lis, Svenja Uhlemeyer, Hermann Blum, Sina Honari, Roland Siegwart, Pascal Fua, Mathieu Salzmann, Matthias Rottmann

State-of-the-art semantic or instance segmentation deep neural networks (DNNs) are usually trained on a closed set of semantic classes.

Instance Segmentation Object +2

Improving Video Instance Segmentation by Light-weight Temporal Uncertainty Estimates

1 code implementation14 Dec 2020 Kira Maag, Matthias Rottmann, Serin Varghese, Fabian Hueger, Peter Schlicht, Hanno Gottschalk

In this paper, we present a time-dynamic approach to model uncertainties of instance segmentation networks and apply this to the detection of false positives as well as the estimation of prediction quality.

Instance Segmentation object-detection +4

Entropy Maximization and Meta Classification for Out-Of-Distribution Detection in Semantic Segmentation

1 code implementation ICCV 2021 Robin Chan, Matthias Rottmann, Hanno Gottschalk

In our experiments we consistently observe a clear additional gain in OoD detection performance, cutting down the number of detection errors by up to 52% when comparing the best baseline with our results.

General Classification Out-of-Distribution Detection +3

A Convenient Infinite Dimensional Framework for Generative Adversarial Learning

no code implementations24 Nov 2020 Hayk Asatryan, Hanno Gottschalk, Marieke Lippert, Matthias Rottmann

In recent years, generative adversarial networks (GANs) have demonstrated impressive experimental results while there are only a few works that foster statistical learning theory for GANs.

Learning Theory

Detection of Iterative Adversarial Attacks via Counter Attack

no code implementations23 Sep 2020 Matthias Rottmann, Kira Maag, Mathis Peyron, Natasa Krejic, Hanno Gottschalk

In this work we outline a mathematical proof that the CW attack can be used as a detector itself.

Detection and Retrieval of Out-of-Distribution Objects in Semantic Segmentation

1 code implementation14 May 2020 Philipp Oberdiek, Matthias Rottmann, Gernot A. Fink

When deploying deep learning technology in self-driving cars, deep neural networks are constantly exposed to domain shifts.

Dimensionality Reduction Image Retrieval +3

MetaFusion: Controlled False-Negative Reduction of Minority Classes in Semantic Segmentation

no code implementations16 Dec 2019 Robin Chan, Matthias Rottmann, Fabian Hüger, Peter Schlicht, Hanno Gottschalk

We present proof-of-concept results for CIFAR-10, and prove the efficiency of our method for the semantic segmentation of street scenes on the Cityscapes dataset based on predicted instances of the 'human' class.

Semantic Segmentation

Time-Dynamic Estimates of the Reliability of Deep Semantic Segmentation Networks

1 code implementation12 Nov 2019 Kira Maag, Matthias Rottmann, Hanno Gottschalk

In the semantic segmentation of street scenes with neural networks, the reliability of predictions is of highest interest.

General Classification Semantic Segmentation +2

The Ethical Dilemma when (not) Setting up Cost-based Decision Rules in Semantic Segmentation

no code implementations2 Jul 2019 Robin Chan, Matthias Rottmann, Radin Dardashti, Fabian Hüger, Peter Schlicht, Hanno Gottschalk

Neural networks for semantic segmentation can be seen as statistical models that provide for each pixel of one image a probability distribution on predefined classes.

Semantic Segmentation

Application of Decision Rules for Handling Class Imbalance in Semantic Segmentation

1 code implementation24 Jan 2019 Robin Chan, Matthias Rottmann, Fabian Hüger, Peter Schlicht, Hanno Gottschalk

We approach such potential misclassifications by weighting the posterior class probabilities with the prior class probabilities which in our case are the inverse frequencies of the corresponding classes in the training dataset.

Semantic Segmentation

Classification Uncertainty of Deep Neural Networks Based on Gradient Information

no code implementations22 May 2018 Philipp Oberdiek, Matthias Rottmann, Hanno Gottschalk

If we however allow the meta classifier to be trained on uncertainty metrics for some out-of-distribution samples, meta classification for concepts remote from EMNIST digits (then termed known unknowns) can be improved considerably.

Classification General Classification +1

Deep Bayesian Active Semi-Supervised Learning

1 code implementation3 Mar 2018 Matthias Rottmann, Karsten Kahl, Hanno Gottschalk

In a setting where a small amount of labeled data as well as a large amount of unlabeled data is available, our method first learns the labeled data set.

Active Learning Data Augmentation

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