Refine
Year of publication
- 2022 (72) (remove)
Document Type
- Conference Proceeding (40)
- Article (reviewed) (10)
- Patent (5)
- Book (4)
- Part of a Book (4)
- Letter to Editor (3)
- Report (3)
- Article (unreviewed) (2)
- Doctoral Thesis (1)
Conference Type
- Konferenzartikel (35)
- Konferenz-Abstract (4)
- Sonstiges (1)
Has Fulltext
- no (72) (remove)
Is part of the Bibliography
- yes (72)
Keywords
- Machine Learning (5)
- Robustness (4)
- Radar (3)
- RoboCup (3)
- Aliasing (2)
- CNNs (2)
- Digitaltechnik (2)
- Felix Mendelssohn Bartholdy (2)
- Geophysik (2)
- Medizintechnik (2)
Institute
- Fakultät Elektrotechnik, Medizintechnik und Informatik (EMI) (ab 04/2019) (72) (remove)
Open Access
- Closed (34)
- Open Access (30)
- Bronze (18)
- Closed Access (8)
- Diamond (5)
- Gold (2)
- Hybrid (1)
Sweaty has already participated several times in RoboCup soccer competitions (Adult Size). Now the work is focused on stabilizing the gait. Moreover, we would like to overcome the constraints of a ZMP-algorithm that has a horizontal footplate as precondition for the simplification of the equations. In addition we would like to switch between impedance and position control with a fuzzy-like algorithm that might help to minimize jerks when Sweaty’s feet touch the ground.
Mit dem Klimaschutzgesetz 2021 wurden von der Bundesregierung die Klimaschutzvorgaben verschärft und die Treibhausgasneutralität bis 2045 als Ziel verankert. Zur Erreichung dieses ambitionierten Ziels ist es notwendig, im Bereich der Mobilität weitgehend von Verbrennungsmotoren mit fossilen Kraftstoffen auf Elektromobilität mit regenerativ erzeugtem Strom umzusteigen. Dabei ist die zügige Bereitstellung einer ausreichenden Ladeinfrastruktur für die Elektrofahrzeuge eine große Herausforderung. Neben der Installation einer ausreichend großen Zahl von Ladepunkten selbst besteht die Herausforderung darin, diese in das bestehende Verteilungsnetz zu integrieren bzw. das Verteilungsnetz so auszubauen, dass weiter ein sicherer Netzbetrieb gewährleistet werden kann. Dabei sind insbesondere Lösungen gefragt, bei denen der Ausbau der Ladeinfrastruktur und der Netzbetriebsmittel durch intelligentes Management des Ladens so gering wie möglich gehalten wird, indem vorhandene oder neu zu installierender Hardware möglichst effizient genutzt wird.
Hier setzte das Projekt „Intelligente Ladeinfrastruktur für Elektrofahrzeuge auf dem Parkplatz der Hochschule Offenburg (INTLOG)“ (Projektlaufzeit 15.11.2020 – 30.09.2022) an. Inhalt des Projekts war es, einen Ladepark für den Parkplatz der Hochschule Offenburg mit 20 Ladepunkten à 11 kW und somit einer Gesamtladeleistung von 220 kW an einen vorhandenen Ortsnetztransformator mit 200 kW Nennleistung anzuschließen, der aber bereits von anderen Verbrauchern genutzt wurde. Das übergeordnete Ziel war es also, eine Ladeinfrastruktur von maßgeblichem Umfang in die bestehende Netzinfrastruktur ohne zusätzlichen Ausbau zu integrieren.
Dabei wurden zukunftsweisende Technologien genutzt und weiterentwickelt sowie teilweise in Praxis, im Labor und in der Computersimulation demonstriert.
Subspace clustering aims to find all clusters in all subspaces of a high-dimensional data space. We present a massively data-parallel approach that can be run on graphics processing units. It extends a previous density-based method that scales well with the number of dimensions. Its main computational bottleneck consists of (sequentially) generating a large number of minimal cluster candidates in each dimension and using hash collisions in order to find matches of such candidates across multiple dimensions. Our approach parallelizes this process by removing previous interdependencies between consecutive steps in the sequential generation process and by applying a very efficient parallel hashing scheme optimized for GPUs. This massive parallelization gives up to 70x speedup for
the bottleneck computation when it is replaced by our approach and run on current GPU hardware. We note that depending on data size and choice of parameters, the parallelized part of the algorithm can take different percentages of the overall runtime of the clustering process, and thus, the overall clustering speedup may vary significantly between different cases. However, even
in our ”worst-case” test, a small dataset where the computation makes up only a small fraction of the overall clustering time, our parallel approach still yields a speedup of more than 3x for the complete run of the clustering process. Our method could also be combined with parallelization of other parts of the clustering algorithm, with an even higher potential gain in processing speed.
Currently, many theoretical as well as practically relevant questions towards the transferability and robustness of Convolutional Neural Networks (CNNs) remain unsolved. While ongoing research efforts are engaging these problems from various angles, in most computer vision related cases these approaches can be generalized to investigations of the effects of distribution shifts in image data. In this context, we propose to study the shifts in the learned weights of trained CNN models. Here we focus on the properties of the distributions of dominantly used 3×3 convolution filter kernels. We collected and publicly provide a dataset with over 1.4 billion filters from hundreds of trained CNNs, using a wide range of datasets, architectures, and vision tasks. In a first use case of the proposed dataset, we can show highly relevant properties of many publicly available pre-trained models for practical applications: I) We analyze distribution shifts (or the lack thereof) between trained filters along different axes of meta-parameters, like visual category of the dataset, task, architecture, or layer depth. Based on these results, we conclude that model pre-training can succeed on arbitrary datasets if they meet size and variance conditions. II) We show that many pre-trained models contain degenerated filters which make them less robust and less suitable for fine-tuning on target applications. Data & Project website: https://github.com/paulgavrikov/cnn-filter-db.
Over the last years, Convolutional Neural Networks (CNNs) have been the dominating neural architecture in a wide range of computer vision tasks. From an image and signal processing point of view, this success might be a bit surprising as the inherent spatial pyramid design of most CNNs is apparently violating basic signal processing laws, i.e. Sampling Theorem in their down-sampling operations. However, since poor sampling appeared not to affect model accuracy, this issue has been broadly neglected until model robustness started to receive more attention. Recent work in the context of adversarial attacks and distribution shifts, showed after all, that there is a strong correlation between the vulnerability of CNNs and aliasing artifacts induced by poor down-sampling operations. This paper builds on these findings and introduces an aliasing free down-sampling operation which can easily be plugged into any CNN architecture: FrequencyLowCut pooling. Our experiments show, that in combination with simple and Fast Gradient Sign Method (FGSM) adversarial training, our hyper-parameter free operator substantially improves model robustness and avoids catastrophic overfitting. Our code is available at https://github.com/GeJulia/flc_pooling
Deep learning models are intrinsically sensitive to distribution shifts in the input data. In particular, small, barely perceivable perturbations to the input data can force models to make wrong predictions with high confidence. An common defense mechanism is regularization through adversarial training which injects worst-case perturbations back into training to strengthen the decision boundaries, and to reduce overfitting. In this context, we perform an investigation of 3 × 3 convolution filters that form in adversarially- trained models. Filters are extracted from 71 public models of the ℓ ∞ -RobustBench CIFAR-10/100 and ImageNet1k leaderboard and compared to filters extracted from models built on the same architectures but trained without robust regularization. We observe that adversarially-robust models appear to form more diverse, less sparse, and more orthogonal convolution filters than their normal counterparts. The largest differences between robust and normal models are found in the deepest layers, and the very first convolution layer, which consistently and predominantly forms filters that can partially eliminate perturbations, irrespective of the architecture.
Despite the success of convolutional neural networks (CNNs) in many academic benchmarks for computer vision tasks, their application in the real-world is still facing fundamental challenges. One of these open problems is the inherent lack of robustness, unveiled by the striking effectiveness of adversarial attacks. Current attack methods are able to manipulate the network's prediction by adding specific but small amounts of noise to the input. In turn, adversarial training (AT) aims to achieve robustness against such attacks and ideally a better model generalization ability by including adversarial samples in the trainingset. However, an in-depth analysis of the resulting robust models beyond adversarial robustness is still pending. In this paper, we empirically analyze a variety of adversarially trained models that achieve high robust accuracies when facing state-of-the-art attacks and we show that AT has an interesting side-effect: it leads to models that are significantly less overconfident with their decisions, even on clean data than non-robust models. Further, our analysis of robust models shows that not only AT but also the model's building blocks (like activation functions and pooling) have a strong influence on the models' prediction confidences. Data & Project website: https://github.com/GeJulia/robustness_confidences_evaluation