Searcharxiv⌕ Search

arXiv subjects

Hanno Gottschalk

Publications and source records attributed to Hanno Gottschalk.

At least 55 records · Page 3Linked to original sources
arXiv2023

Optimal control of thermal and mechanical loads in activation processes of mechanical components

This paper develops a mathematical framework that aims to control the temperature and rotational speed in the activation process of a gas turbine in an optimal way. These controls influence the deformation and the stress in the component due to centripetal loads and transient thermal stress. An optimal control problem is formulated as the minimization of maximal von Mises stress over a given time and over the whole component. To find a solution for this, we need to solve the linear thermoelasticity and the heat equations using the finite element method. The results for the optimal control as functions of the rotation speed and external gas temperature over time are computed by sequential quadratic programming, where gradients are computed using finite differences.The overall outcome reveals a significant reduction of approximately 10\%, from $830 \frac{N}{mm^2}$ to $750 \frac{N}{mm^2}$, in von Mises stress by controlling two parameters, along with the temporal separation of physical control phenomena.

math.OC↗
arXiv2023

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. In applications like autonomous driving, where video data is available, convolutional long short-term memory networks are capable of not only providing semantic segmentations but also predicting the segmentations of the next timesteps. These models use cell states to broadcast information from previous data by taking a time series of inputs to predict one or even further steps into the future. We present a temporal postprocessing method which estimates the prediction performance of convolutional long short-term memory networks by either predicting the intersection over union of predicted and ground truth segments or classifying between intersection over union being equal to zero or greater than zero. To this end, we create temporal cell state-based input metrics per segment and investigate different models for the estimation of the predictive quality based on these metrics. We further study the influence of the number of considered cell states for the proposed metrics.

cs.CV↗
arXiv2023

Have We Ever Encountered This Before? Retrieving Out-of-Distribution Road Obstacles from Driving Scenes

In the life cycle of highly automated systems operating in an open and dynamic environment, the ability to adjust to emerging challenges is crucial. For systems integrating data-driven AI-based components, rapid responses to deployment issues require fast access to related data for testing and reconfiguration. In the context of automated driving, this especially applies to road obstacles that were not included in the training data, commonly referred to as out-of-distribution (OoD) road obstacles. Given the availability of large uncurated recordings of driving scenes, a pragmatic approach is to query a database to retrieve similar scenarios featuring the same safety concerns due to OoD road obstacles. 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. Our proposed method leverages the recent advances in OoD segmentation and multi-modal foundation models to identify and efficiently extract safety-relevant scenes from unlabeled videos. We present a first approach for the novel task of text-based OoD object retrieval, which addresses the question ''Have we ever encountered this before?''.

cs.CV↗
arXiv2023

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. It can also be used to modify existing architectures and has the capability to remove and insert ResNet blocks, in this way searching for suitable architectures in the space of ResNet architectures. In our experiments on different image classification datasets, Resbuilder achieves close to state-of-the-art performance while saving computational cost compared to off-the-shelf ResNets. Noteworthy, we once tune the parameters on CIFAR10 which yields a suitable default choice for all other datasets. We demonstrate that this property generalizes even to industrial applications by applying our method with default parameters on a proprietary fraud detection dataset.

cs.LG↗
arXiv2023

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}. Our results show that incorporating these corner cases during training improves the recognition of corner cases during testing, even though, they were recorded due to visual impairment. Using the corner case triggering pipeline developed in the previous work, we investigate the effectiveness of using expert models to overcome the domain gap due to different weather conditions and times of day, compared to a universal model from a development perspective. Our study reveals that expert models can provide significant benefits in terms of performance and efficiency, and can reduce the time and effort required for model training. Our results contribute to the progress of automated driving, providing a pathway for safer and more reliable autonomous vehicles on the road in the future.

cs.CV↗
arXiv2023

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. Furthermore, the importance of the domain gap between two different image sources is considered, as it is important to create usability independent of hardware components such as the high-resolution scanner used. Since for the application of machine learning methods, alterations of scanner-specific properties such as brightness, contrast or sharpness can have strong (negative) effects on the quality of the prediction methods, two ways to overcome this domain gap are discussed in this paper.

eess.IV↗
arXiv2023

Cosmological de Sitter Solutions of the Semiclassical Einstein Equation

Exponentially expanding space-times play a central role in contemporary cosmology, most importantly in the theory of inflation and in the Dark Energy driven expansion in the late universe. In this work, we give a complete list of de Sitter solutions of the semiclassical Einstein equation (SCE), where classical gravity is coupled to the expected value of a renormalized stress-energy tensor of a free quantum field in the Bunch-Davies state. To achieve this, we explicitly determine the stress-energy tensor associated with the Bunch-Davies state using the recently proposed `moment approach' on the cosmological coordinate patch of de Sitter space. From the energy component of the SCE we thus obtain an analytic consistency equation for the model's parameters which has to be fulfilled by solutions to the SCE. Using this equation we then investigate the number of solutions and the structure of the solution set in dependency on the coupling parameter of the quantum field to the scalar curvature and renormalization constants using analytic arguments in combination with numerical evidence. We also identify parameter sets where multiple expansion rates separated by several orders of magnitude are possible. Potentially for such parameter settings, a fast (semi-stable) expansion in the early universe could be compatible with a late time `Dark Energy-like' behavior of the universe.

gr-qc↗
arXiv2023

Detecting Novelties with Empty Classes

For open world applications, deep neural networks (DNNs) need to be aware of previously unseen data and adaptable to evolving environments. Furthermore, it is desirable to detect and learn novel classes which are not included in the DNNs underlying set of semantic classes in an unsupervised fashion. The method proposed in this article builds upon anomaly detection to retrieve out-of-distribution (OoD) data as candidates for new classes. We thereafter extend the DNN by $k$ empty classes and fine-tune it on the OoD data samples. To this end, we introduce two loss functions, which 1) entice the DNN to assign OoD samples to the empty classes and 2) to minimize the inner-class feature distances between them. Thus, instead of ground truth which contains labels for the different novel classes, the DNN obtains a single OoD label together with a distance matrix, which is computed in advance. We perform several experiments for image classification and semantic segmentation, which demonstrate that a DNN can extend its own semantic space by multiple classes without having access to ground truth.

cs.CV↗
arXiv2023

Survey on Unsupervised Domain Adaptation for Semantic Segmentation for Visual Perception in Automated Driving

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 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. Despite this progress and tremendous research efforts, several issues still need to be addressed that limit the applicability of DNNs in automated driving. The bad generalization of DNNs to new, unseen domains is a major problem on the way to a safe, large-scale application, because manual annotation of new domains is costly, particularly for semantic segmentation. For this reason, methods are required to adapt DNNs to new domains without labeling effort. The task, which these methods aim to solve is termed unsupervised domain adaptation (UDA). While several different domain shifts can challenge DNNs, the shift between synthetic and real data is of particular importance for automated driving, as it allows the use of simulation environments for DNN training. In this work, we present an overview of the current state of the art in this field of research. We categorize and explain the different approaches for UDA. The number of considered publications is larger than any other survey on this topic. The scope of this survey goes far beyond the description of the UDA state-of-the-art. Based on our large data and knowledge base, we present a quantitative comparison of the approaches and use the observations to point out the latest trends in this field. In the following, we conduct a critical analysis of the state-of-the-art and highlight promising future research directions. With this survey, we aim to facilitate UDA research further and encourage scientists to exploit novel research directions to generalize DNNs better.

cs.CV↗
arXiv2023

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. While UDA methods have access to unlabeled target images, domain generalization does not involve any target data and only learns generalized features from a source domain. Image-style randomization or augmentation is a popular approach to improve network generalization without access to the target domain. Complex methods are often proposed that disregard the potential of simple image augmentations for out-of-domain generalization. For this reason, we systematically study the in- and out-of-domain generalization capabilities of simple, rule-based image augmentations like blur, noise, color jitter and many more. Based on a full factorial design of experiment design we provide a systematic statistical evaluation of augmentations and their interactions. Our analysis provides both, expected and unexpected, outcomes. Expected, because our experiments confirm the common scientific standard that combination of multiple different augmentations out-performs single augmentations. Unexpected, because combined augmentations perform competitive to state-of-the-art domain generalization approaches, while being significantly simpler and without training overhead. On the challenging synthetic-to-real domain shift between Synthia and Cityscapes we reach 39.5% mIoU compared to 40.9% mIoU of the best previous work. When additionally employing the recent vision transformer architecture DAFormer we outperform these benchmarks with a performance of 44.2% mIoU

cs.CV↗
arXiv2023

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. Overcoming less suitable local minima is an important prerequisite and often momentum methods are employed to achieve this. As in other non local optimization procedures, this however creates the necessity to balance between exploration and exploitation. In this work, we suggest an event based control mechanism for switching from exploration to exploitation based on reaching a predefined reduction of the loss function. As we give the momentum method a port Hamiltonian interpretation, we apply the 'heavy ball with friction' interpretation and trigger breaking (or friction) when achieving certain goals. We benchmark our method against standard stochastic gradient descent and provide experimental evidence for improved performance of deep neural networks when our strategy is applied.

cs.LG↗
arXiv2023

Non-convex shape optimization by dissipative Hamiltonian flows

Shape optimization with constraints given by partial differential equations (PDE) is a highly developed field of optimization theory. The elegant adjoint formalism allows to compute shape gradients at the computational cost of a further PDE solve. Thus, gradient descent methods can be applied to shape optimization problems. However, gradient descent methods that can be understood as approximation to gradient flows get stuck in local minima, if the optimization problem is non-convex. In machine learning, the optimization in high dimensional non-convex energy landscapes has been successfully tackled by momentum methods, which can be understood as passing from gradient flow to dissipative Hamiltonian flows. In this paper, we adopt this strategy for non-convex shape optimization. In particular, we provide a mechanical shape optimization problem that is motivated by optimal reliability considering also material cost and the necessity to avoid certain obstructions in installation space. We then show how this problem can be solved effectively by port Hamiltonian shape flows.

math.OC↗
arXiv2023

LU-Net: Invertible Neural Networks Based on Matrix Factorization

LU-Net is a simple and fast architecture for invertible neural networks (INN) that is based on the factorization of quadratic weight matrices $\mathsf{A=LU}$, where $\mathsf{L}$ is a lower triangular matrix with ones on the diagonal and $\mathsf{U}$ an upper triangular matrix. Instead of learning a fully occupied matrix $\mathsf{A}$, we learn $\mathsf{L}$ and $\mathsf{U}$ separately. If combined with an invertible activation function, such layers can easily be inverted whenever the diagonal entries of $\mathsf{U}$ are different from zero. Also, the computation of the determinant of the Jacobian matrix of such layers is cheap. Consequently, the LU architecture allows for cheap computation of the likelihood via the change of variables formula and can be trained according to the maximum likelihood principle. In our numerical experiments, we test the LU-net architecture as generative model on several academic datasets. We also provide a detailed comparison with conventional invertible neural networks in terms of performance, training as well as run time.

cs.LG↗
arXiv2023

Generalization capabilities of conditional GAN for turbulent flow under changes of geometry

Turbulent flow consists of structures with a wide range of spatial and temporal scales which are hard to resolve numerically. Classical numerical methods as the Large Eddy Simulation (LES) are able to capture fine details of turbulent structures but come at high computational cost. Applying generative adversarial networks (GAN) for the synthetic modeling of turbulence is a mathematically well-founded approach to overcome this issue. In this work, we investigate the generalization capabilites of GAN-based synthetic turbulence generators when geometrical changes occur in the flow configuration (e.g. aerodynamic geometric optimization of structures such as airfoils). As training data, we use the flow around a low-pressure turbine (LPT) stator with periodic wake impact obtained from highly resolved LES. To simulate the flow around a LPT stator, we use the conditional deep convolutional GAN framework pix2pixHD conditioned on the position of a rotating wake in front of the stator. For the generalization experiments we exclude images of wake positions located at certain regions from the training data and use the unseen data for testing. We show the abilities and limits of generalization for the conditional GAN by extending the regions of the extracted wake positions successively. Finally, we evaluate the statistical properties of the synthesized flow field by comparison with the corresponding LES results.

physics.flu-dyn↗
arXiv2023

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. In this work, we propose an infinite dimensional theoretical framework for generative adversarial learning. We assume that the probability density functions of the underlying measure are uniformly bounded, $k$-times $α$-Hölder differentiable ($C^{k,α}$) and uniformly bounded away from zero. Under these assumptions, we show that the Rosenblatt transformation induces an optimal generator, which is realizable in the hypothesis space of $C^{k,α}$-generators. With a consistent definition of the hypothesis space of discriminators, we further show that the Jensen-Shannon divergence between the distribution induced by the generator from the adversarial learning procedure and the data generating distribution converges to zero. Under certain regularity assumptions on the density of the data generating process, we also provide rates of convergence based on chaining and concentration.

cs.LG↗
arXiv2023

Equivariant and Steerable Neural Networks: A review with special emphasis on the symmetric group

Convolutional neural networks revolutionized computer vision and natrual language processing. Their efficiency, as compared to fully connected neural networks, has its origin in the architecture, where convolutions reflect the translation invariance in space and time in pattern or speech recognition tasks. Recently, Cohen and Welling have put this in the broader perspective of invariance under symmetry groups, which leads to the concept of group equivaiant neural networks and more generally steerable neural networks. In this article, we review the architecture of such networks including equivariant layers and filter banks, activation with capsules and group pooling. We apply this formalism to the symmetric group, for which we work out a number of details on representations and capsules that are not found in the literature.

cs.LG↗
arXiv2022

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. Development of active learning methods in such fields is highly computationally expensive and time consuming which obstructs the progression of research and leads to a lack of comparability between methods. In this work, we propose and investigate a sandbox setup for rapid development and transparent evaluation of active learning in deep object detection. Our experiments with commonly used configurations of datasets and detection architectures found in the literature show that results obtained in our sandbox environment are representative of results on standard configurations. The total compute time to obtain results and assess the learning behavior can thereby be reduced by factors of up to 14 when comparing with Pascal VOC and up to 32 when comparing with BDD100k. This allows for testing and evaluating data acquisition and labeling strategies in under half a day and contributes to the transparency and development speed in the field of active learning for object detection.

cs.CV↗
arXiv2022

A-Eye: Driving with the Eyes of AI for Corner Case Generation

The overall goal of this work is to enrich training data for automated driving with so called corner cases. In road traffic, corner cases are critical, rare and unusual situations that challenge the perception by AI algorithms. For this purpose, we present the design of a test rig to generate synthetic corner cases using a human-in-the-loop approach. 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. In addition, a second person gets to see the same scene from the original CARLA output and is supposed to intervene with the help of a second control unit as soon as the semantic driver shows dangerous driving behavior. Interventions potentially indicate poor recognition of a critical scene by the segmentation network and then represents a corner case. In our experiments, we show that targeted enrichment of training data with corner cases leads to improvements in pedestrian detection in safety relevant episodes in road traffic.

cs.CV↗