Search Results for author:
Found 40 papers, 11 papers with code
VLTSeg: Simple Transfer of CLIP-Based Vision-Language Representations for Domain Generalized Semantic Segmentation
We thus propose a new vision-language approach for domain generalized segmentation, which improves the domain generalization SOTA by 7. 6% mIoU when training on the synthetic GTA5 dataset.
Ranked #1 on
Semantic Segmentation
on Cityscapes test
(using extra training data)
Temporal Performance Prediction for Deep Convolutional Long Short-Term Memory Networks
Quantifying predictive uncertainty of deep semantic segmentation networks is essential in safety-critical tasks.
Have We Ever Encountered This Before? Retrieving Out-of-Distribution Road Obstacles from Driving Scenes
In this work, we extend beyond identifying OoD road obstacles in video streams and offer a comprehensive approach to extract sequences of OoD road obstacles using text queries, thereby proposing a way of curating a collection of OoD data for subsequent analysis.
ResBuilder: Automated Learning of Depth with Residual Structures
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.
survAIval: Survival Analysis with the Eyes of AI
In this study, we propose a novel approach to enrich the training data for automated driving by using a self-designed driving simulator and two human drivers to generate safety-critical corner cases in a short period of time, as already presented in~\cite{kowol22simulator}.
Risk stratification of malignant melanoma using neural networks
In order to improve the detection and classification of malignant melanoma, this paper describes an image-based method that can achieve AUROC values of up to 0. 78 without additional clinical information.
Detecting Novelties with Empty Classes
We thereafter extend the DNN by $k$ empty classes and fine-tune it on the OoD data samples.
Survey on Unsupervised Domain Adaptation for Semantic Segmentation for Visual Perception in Automated Driving
DNNs play a significant role in environment perception for the challenging application of automated driving and are employed for tasks such as detection, semantic segmentation, and sensor fusion.
Augmentation-based Domain Generalization for Semantic Segmentation
Unsupervised Domain Adaptation (UDA) and domain generalization (DG) are two research areas that aim to tackle the lack of generalization of Deep Neural Networks (DNNs) towards unseen domains.
Who breaks early, looses: goal oriented training of deep neural networks based on port Hamiltonian dynamics
The highly structured energy landscape of the loss as a function of parameters for deep neural networks makes it necessary to use sophisticated optimization strategies in order to discover (local) minima that guarantee reasonable performance.
LU-Net: Invertible Neural Networks Based on Matrix Factorization
Also, the computation of the determinant of the Jacobian matrix of such layers is cheap.
Generalization capabilities of conditional GAN for turbulent flow under changes of geometry
As training data, we use the flow around a low-pressure turbine (LPT) stator with periodic wake impact obtained from highly resolved LES.
Equivariant and Steerable Neural Networks: A review with special emphasis on the symmetric group
Convolutional neural networks revolutionized computer vision and natrual language processing.
Towards Rapid Prototyping and Comparability in Active Learning for Deep Object Detection
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.
Two Video Data Sets for Tracking and Retrieval of Out of Distribution Objects
We present the SOS data set containing 20 video sequences of street scenes and more than 1000 labeled frames with up to two OOD objects.
Semi-supervised domain adaptation with CycleGAN guided by a downstream task loss
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.
What should AI see? Using the Public's Opinion to Determine the Perception of an AI
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.
Uncertainty Quantification and Resource-Demanding Computer Vision Applications of Deep Learning
Training deep neural networks is already resource demanding and so is also their uncertainty quantification.
A-Eye: Driving with the Eyes of AI for Corner Case Generation
For the test rig, a real-time semantic segmentation network is trained and integrated into the driving simulation software CARLA in such a way that a human can drive on the network's prediction.
Detecting and Learning the Unknown in Semantic Segmentation
However, this is in contrast to the open world assumption in automated driving that DNNs are deployed to.
Towards Unsupervised Open World Semantic Segmentation
More precisely, the connected components of a predicted semantic segmentation are assessed by a segmentation quality estimate.
Does Redundancy in AI Perception Systems Help to Test for Super-Human Automated Driving Performance?
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.
Generative Modeling of Turbulence
Based on this analysis, we study a hierarchy of chaotic systems starting with the Lorenz attractor and then carry on to the modeling of turbulent flows with GAN.
False Positive Detection and Prediction Quality Estimation for LiDAR Point Cloud Segmentation
We present a novel post-processing tool for semantic segmentation of LiDAR point cloud data, called LidarMetaSeg, which estimates the prediction quality segmentwise.
Background-Foreground Segmentation for Interior Sensing in Automotive Industry
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.
Gradient-Based Quantification of Epistemic Uncertainty for Deep Object Detectors
The vast majority of uncertainty quantification methods for deep object detectors such as variational inference are based on the network output.
Improving Video Instance Segmentation by Light-weight Temporal Uncertainty Estimates
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.
Entropy Maximization and Meta Classification for Out-Of-Distribution Detection in Semantic Segmentation
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.
A Convenient Infinite Dimensional Framework for Generative Adversarial Learning
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.
YOdar: Uncertainty-based Sensor Fusion for Vehicle Detection with Camera and Radar Sensors
In this work, we present an uncertainty-based method for sensor fusion with camera and radar data.
MetaBox+: A new Region Based Active Learning Method for Semantic Segmentation using Priority Maps
The comparison and analysis of the results provide insights into annotation costs as well as robustness and variance of the methods.
Detection of Iterative Adversarial Attacks via Counter Attack
In this work we outline a mathematical proof that the CW attack can be used as a detector itself.
MetaFusion: Controlled False-Negative Reduction of Minority Classes in Semantic Segmentation
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.
Detection of False Positive and False Negative Samples in Semantic Segmentation
In recent years, deep learning methods have outperformed other methods in image recognition.
Time-Dynamic Estimates of the Reliability of Deep Semantic Segmentation Networks
In the semantic segmentation of street scenes with neural networks, the reliability of predictions is of highest interest.
The Ethical Dilemma when (not) Setting up Cost-based Decision Rules in Semantic Segmentation
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.
Application of Decision Rules for Handling Class Imbalance in Semantic Segmentation
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.
Prediction Error Meta Classification in Semantic Segmentation: Detection via Aggregated Dispersion Measures of Softmax Probabilities
We aggregate these dispersion measures segment-wise and derive metrics that are well-correlated with the segment-wise IoU of prediction and ground truth.
Classification Uncertainty of Deep Neural Networks Based on Gradient Information
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.
Deep Bayesian Active Semi-Supervised Learning
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.
