61 citations · 277 across the 41 of their papers we have counts for
10 papers · 1 filter
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…