61 citations · 277 across the 41 of their papers we have counts for
46 papers
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…
Employing Real Training Data for Deep Noise Suppression
Ziyi Xu, Marvin Sach, Jan Pirklbauer +1
Most deep noise suppression (DNS) models are trained with reference-based losses requiring access to clean speech. However, sometimes an additive microphone model is insufficient f…
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…
Efficient Acoustic Echo Suppression with Condition-Aware Training
Ernst Seidel, Pejman Mowlaee, Tim Fingscheidt
The topic of deep acoustic echo control (DAEC) has seen many approaches with various model topologies in recent years. Convolutional recurrent networks (CRNs), consisting of a conv…
EffCRN: An Efficient Convolutional Recurrent Network for High-Performance Speech Enhancement
Marvin Sach, Jan Franzen, Bruno Defraene +4
Fully convolutional recurrent neural networks (FCRNs) have shown state-of-the-art performance in single-channel speech enhancement. However, the number of parameters and the FLOPs/…
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…
Coded Speech Quality Measurement by a Non-Intrusive PESQ-DNN
Ziyi Xu, Ziyue Zhao, Tim Fingscheidt
Wideband codecs such as AMR-WB or EVS are widely used in (mobile) speech communication. Evaluation of coded speech quality is often performed subjectively by an absolute category r…
Relaxed Attention for Transformer Models
Timo Lohrenz, Björn Möller, Zhengyang Li +1
The powerful modeling capabilities of all-attention-based transformer architectures often cause overfitting and - for natural language processing tasks - lead to an implicitly lear…
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…
Does a PESQNet (Loss) Require a Clean Reference Input? The Original PESQ Does, But ACR Listening Tests Don't
Ziyi Xu, Maximilian Strake, Tim Fingscheidt
Perceptual evaluation of speech quality (PESQ) requires a clean speech reference as input, but predicts the results from (reference-free) absolute category rating (ACR) tests. In t…
Bandwidth-Scalable Fully Mask-Based Deep FCRN Acoustic Echo Cancellation and Postfiltering
Ernst Seidel, Rasmus Kongsgaard Olsson, Karim Haddad +3
Although today's speech communication systems support various bandwidths from narrowband to super-wideband and beyond, state-of-the art DNN methods for acoustic echo cancellation (…
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…
Reconfigurable Intelligent Surface Enabled Spatial Multiplexing with Fully Convolutional Network
Bile Peng, Jan-Aike Termöhlen, Cong Sun +4
Reconfigurable intelligent surface (RIS) is an emerging technology for future wireless communication systems. In this work, we consider downlink spatial multiplexing enabled by the…
Deep Noise Suppression Maximizing Non-Differentiable PESQ Mediated by a Non-Intrusive PESQNet
Ziyi Xu, Maximilian Strake, Tim Fingscheidt
Speech enhancement employing deep neural networks (DNNs) for denoising are called deep noise suppression (DNS). During training, DNS methods are typically trained with mean squared…
Description of Corner Cases in Automated Driving: Goals and Challenges
Daniel Bogdoll, Jasmin Breitenstein, Florian Heidecker +4
Scaling the distribution of automated vehicles requires handling various unexpected and possibly dangerous situations, termed corner cases (CC). Since many modules of automated dri…
Deep Residual Echo Suppression and Noise Reduction: A Multi-Input FCRN Approach in a Hybrid Speech Enhancement System
Jan Franzen, Tim Fingscheidt
Deep neural network (DNN)-based approaches to acoustic echo cancellation (AEC) and hybrid speech enhancement systems have gained increasing attention recently, introducing signific…
Relaxed Attention: A Simple Method to Boost Performance of End-to-End Automatic Speech Recognition
Timo Lohrenz, Patrick Schwarz, Zhengyang Li +1
Recently, attention-based encoder-decoder (AED) models have shown high performance for end-to-end automatic speech recognition (ASR) across several tasks. Addressing overconfidence…
Inspect, Understand, Overcome: A Survey of Practical Methods for AI Safety
Sebastian Houben, Stephanie Abrecht, Maram Akila +38
The use of deep neural networks (DNNs) in safety-critical applications like mobile health and autonomous driving is challenging due to numerous model-inherent shortcomings. These s…
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…
Multi-Encoder Learning and Stream Fusion for Transformer-Based End-to-End Automatic Speech Recognition
Timo Lohrenz, Zhengyang Li, Tim Fingscheidt
Stream fusion, also known as system combination, is a common technique in automatic speech recognition for traditional hybrid hidden Markov model approaches, yet mostly unexplored…