61 citations · 277 across the 41 of their papers we have counts for
25 papers · 1 filter
Generalization by Adaptation: Diffusion-Based Domain Extension for Domain-Generalized Semantic Segmentation
Joshua Niemeijer, Manuel Schwonberg, Jan-Aike Termöhlen +2
When models, e.g., for semantic segmentation, are applied to images that are vastly different from training data, the performance will drop significantly. Domain adaptation methods…
A Re-Parameterized Vision Transformer (ReVT) for Domain-Generalized Semantic Segmentation
Jan-Aike Termöhlen, Timo Bartels, Tim Fingscheidt
The task of semantic segmentation requires a model to assign semantic labels to each pixel of an image. However, the performance of such models degrades when deployed in an unseen…
Survey on Unsupervised Domain Adaptation for Semantic Segmentation for Visual Perception in Automated Driving
Manuel Schwonberg, Joshua Niemeijer, Jan-Aike Termöhlen +4
Deep neural networks (DNNs) have proven their capabilities in many areas in the past years, such as robotics, or automated driving, enabling technological breakthroughs. DNNs play…
On the Choice of Data for Efficient Training and Validation of End-to-End Driving Models
Marvin Klingner, Konstantin Müller, Mona Mirzaie +3
The emergence of data-driven machine learning (ML) has facilitated significant progress in many complicated tasks such as highly-automated driving. While much effort is put into im…
Amodal Cityscapes: A New Dataset, its Generation, and an Amodal Semantic Segmentation Challenge Baseline
Jasmin Breitenstein, Tim Fingscheidt
Amodal perception terms the ability of humans to imagine the entire shapes of occluded objects. This gives humans an advantage to keep track of everything that is going on, especia…
Detecting Adversarial Perturbations in Multi-Task Perception
Marvin Klingner, Varun Ravi Kumar, Senthil Yogamani +2
While deep neural networks (DNNs) achieve impressive performance on environment perception tasks, their sensitivity to adversarial perturbations limits their use in practical appli…
Continual BatchNorm Adaptation (CBNA) for Semantic Segmentation
Marvin Klingner, Mouadh Ayache, Tim Fingscheidt
Environment perception in autonomous driving vehicles often heavily relies on deep neural networks (DNNs), which are subject to domain shifts, leading to a significantly decreased…
Improving Performance of Semantic Segmentation CycleGANs by Noise Injection into the Latent Segmentation Space
Jonas Löhdefink, Tim Fingscheidt
In recent years, semantic segmentation has taken benefit from various works in computer vision. Inspired by the very versatile CycleGAN architecture, we combine semantic segmentati…
Improving Online Performance Prediction for Semantic Segmentation
Marvin Klingner, Andreas Bär, Marcel Mross +1
In this work we address the task of observing the performance of a semantic segmentation deep neural network (DNN) during online operation, i.e., during inference, which is of high…
SVDistNet: Self-Supervised Near-Field Distance Estimation on Surround View Fisheye Cameras
Varun Ravi Kumar, Marvin Klingner, Senthil Yogamani +4
A 360° perception of scene geometry is essential for automated driving, notably for parking and urban driving scenarios. Typically, it is achieved using surround-view fisheye camer…
An Application-Driven Conceptualization of Corner Cases for Perception in Highly Automated Driving
Florian Heidecker, Jasmin Breitenstein, Kevin Rösch +5
Systems and functions that rely on machine learning (ML) are the basis of highly automated driving. An essential task of such ML models is to reliably detect and interpret unusual,…
Corner Cases for Visual Perception in Automated Driving: Some Guidance on Detection Approaches
Jasmin Breitenstein, Jan-Aike Termöhlen, Daniel Lipinski +1
Automated driving has become a major topic of interest not only in the active research community but also in mainstream media reports. Visual perception of such intelligent vehicle…
The Vulnerability of Semantic Segmentation Networks to Adversarial Attacks in Autonomous Driving: Enhancing Extensive Environment Sensing
Andreas Bär, Jonas Löhdefink, Nikhil Kapoor +4
Enabling autonomous driving (AD) can be considered one of the biggest challenges in today's technology. AD is a complex task accomplished by several functionalities, with environme…
A Self-Supervised Feature Map Augmentation (FMA) Loss and Combined Augmentations Finetuning to Efficiently Improve the Robustness of CNNs
Nikhil Kapoor, Chun Yuan, Jonas Löhdefink +6
Deep neural networks are often not robust to semantically-irrelevant changes in the input. In this work we address the issue of robustness of state-of-the-art deep convolutional ne…
From a Fourier-Domain Perspective on Adversarial Examples to a Wiener Filter Defense for Semantic Segmentation
Nikhil Kapoor, Andreas Bär, Serin Varghese +4
Despite recent advancements, deep neural networks are not robust against adversarial perturbations. Many of the proposed adversarial defense approaches use computationally expensiv…
Unsupervised BatchNorm Adaptation (UBNA): A Domain Adaptation Method for Semantic Segmentation Without Using Source Domain Representations
Marvin Klingner, Jan-Aike Termöhlen, Jacob Ritterbach +1
In this paper we present a solution to the task of "unsupervised domain adaptation (UDA) of a given pre-trained semantic segmentation model without relying on any source domain rep…
Transferable Universal Adversarial Perturbations Using Generative Models
Atiye Sadat Hashemi, Andreas Bär, Saeed Mozaffari +1
Deep neural networks tend to be vulnerable to adversarial perturbations, which by adding to a natural image can fool a respective model with high confidence. Recently, the existenc…
SynDistNet: Self-Supervised Monocular Fisheye Camera Distance Estimation Synergized with Semantic Segmentation for Autonomous Driving
Varun Ravi Kumar, Marvin Klingner, Senthil Yogamani +3
State-of-the-art self-supervised learning approaches for monocular depth estimation usually suffer from scale ambiguity. They do not generalize well when applied on distance estima…
Self-Supervised Monocular Depth Estimation: Solving the Dynamic Object Problem by Semantic Guidance
Marvin Klingner, Jan-Aike Termöhlen, Jonas Mikolajczyk +1
Self-supervised monocular depth estimation presents a powerful method to obtain 3D scene information from single camera images, which is trainable on arbitrary image sequences with…
openDD: A Large-Scale Roundabout Drone Dataset
Antonia Breuer, Jan-Aike Termöhlen, Silviu Homoceanu +1
Analyzing and predicting the traffic scene around the ego vehicle has been one of the key challenges in autonomous driving. Datasets including the trajectories of all road users pr…
Self-Supervised Domain Mismatch Estimation for Autonomous Perception
Jonas Löhdefink, Justin Fehrling, Marvin Klingner +4
Autonomous driving requires self awareness of its perception functions. Technically spoken, this can be realized by observers, which monitor the performance indicators of various p…
Class-Incremental Learning for Semantic Segmentation Re-Using Neither Old Data Nor Old Labels
Marvin Klingner, Andreas Bär, Philipp Donn +1
While neural networks trained for semantic segmentation are essential for perception in autonomous driving, most current algorithms assume a fixed number of classes, presenting a m…
Improved Noise and Attack Robustness for Semantic Segmentation by Using Multi-Task Training with Self-Supervised Depth Estimation
Marvin Klingner, Andreas Bär, Tim Fingscheidt
While current approaches for neural network training often aim at improving performance, less focus is put on training methods aiming at robustness towards varying noise conditions…
Towards Corner Case Detection for Autonomous Driving
Jan-Aike Bolte, Andreas Bär, Daniel Lipinski +1
The progress in autonomous driving is also due to the increased availability of vast amounts of training data for the underlying machine learning approaches. Machine learning syste…