Refine
Year of publication
Document Type
- Conference Proceeding (19)
- Article (9)
- Part of a Book (3)
- Doctoral Thesis (3)
- Master's Thesis (2)
- Bachelor Thesis (1)
- Book (1)
- Preprint (1)
- Report (1)
Keywords
- 3D ship detection (1)
- Bayesian convolutional neural networks (1)
- Bayesian neural network (1)
- Calibration procedure (1)
- Classification (1)
- Computer vision (1)
- Convolutional networks (1)
- Crowdmanagement (1)
- Deep Transformation Model (1)
- Deep learning (5)
- Defect detection (1)
- Didaktik (2)
- Environmental perception (1)
- Extended object tracking (1)
- Extension estimation (1)
- Finite-element (1)
- Forest establishment (1)
- Freistellungssemesterbericht (1)
- GPU (1)
- Gaussian processes (1)
- Ground detection (1)
- Image novelty detection (1)
- Imaging (1)
- Interpretability (1)
- Inverse perspective (1)
- Ischemic stroke (1)
- Learning to cluster (1)
- LernApp (1)
- Lidar (2)
- Lidar-camera registration (1)
- Machine Learning (1)
- Machine learning (1)
- Magnetic resonance imaging (1)
- Mashine learning (1)
- Mask R-CNN (1)
- Mathematik (1)
- Mean-shift (1)
- Mirror (1)
- Mobile robot (1)
- Modelling (1)
- Multi-camera (1)
- Multivariate Differentiation (1)
- Mutual information (1)
- Normalizing Flow (1)
- Object detection (1)
- Pedestrian (1)
- Perceptual grouping (1)
- Personenstromsimulation (1)
- Probabilistic modeling (1)
- Random matrices (1)
- Real-time (1)
- Reconstruction (1)
- Recurrent neural network (1)
- Regression (1)
- Screening (1)
- Seamless Learning (2)
- Segmentation (1)
- Sensor fusion (1)
- Ship dataset (1)
- Speaker clustering (1)
- Speaker recognition (1)
- Speech & image clustering (1)
- Statistics (1)
- Stereo-matching (1)
- Surrogate Modell (1)
- Transformation models (1)
- Tree seedlings (1)
- Un-certainty (1)
- Uncertainty (1)
- Unmanned aerial vehicles (1)
- Variational inference (1)
Institute
- Institut für Optische Systeme - IOS (40) (remove)
Black-box variational inference (BBVI) is a technique to approximate the posterior of Bayesian models by optimization. Similar to MCMC, the user only needs to specify the model; then, the inference procedure is done automatically. In contrast to MCMC, BBVI scales to many observations, is faster for some applications, and can take advantage of highly optimized deep learning frameworks since it can be formulated as a minimization task. In the case of complex posteriors, however, other state-of-the-art BBVI approaches often yield unsatisfactory posterior approximations. This paper presents Bernstein flow variational inference (BF-VI), a robust and easy-to-use method flexible enough to approximate complex multivariate posteriors. BF-VI combines ideas from normalizing flows and Bernstein polynomial-based transformation models. In benchmark experiments, we compare BF-VI solutions with exact posteriors, MCMC solutions, and state-of-the-art BBVI methods, including normalizing flow-based BBVI. We show for low-dimensional models that BF-VI accurately approximates the true posterior; in higher-dimensional models, BF-VI compares favorably against other BBVI methods. Further, using BF-VI, we develop a Bayesian model for the semi-structured melanoma challenge data, combining a CNN model part for image data with an interpretable model part for tabular data, and demonstrate, for the first time, the use of BBVI in semi-structured models.
Incremental one-class learning using regularized null-space training for industrial defect detection
(2024)
One-class incremental learning is a special case of class-incremental learning, where only a single novel class is incrementally added to an existing classifier instead of multiple classes. This case is relevant in industrial defect detection scenarios, where novel defects usually appear during operation. Existing rolled-out classifiers must be updated incrementally in this scenario with only a few novel examples. In addition, it is often required that the base classifier must not be altered due to approval and warranty restrictions. While simple finetuning often gives the best performance across old and new classes, it comes with the drawback of potentially losing performance on the base classes (catastrophic forgetting [1]). Simple prototype approaches [2] work without changing existing weights and perform very well when the classes are well separated but fail dramatically when not. In theory, null-space training (NSCL) [3] should retain the basis classifier entirely, as parameter updates are restricted to the null space of the network with respect to existing classes. However, as we show, this technique promotes overfitting in the case of one-class incremental learning. In our experiments, we found that unconstrained weight growth in null space is the underlying issue, leading us to propose a regularization term (R-NSCL) that penalizes the magnitude of amplification. The regularization term is added to the standard classification loss and stabilizes null-space training in the one-class scenario by counteracting overfitting. We test the method’s capabilities on two industrial datasets, namely AITEX and MVTec, and compare the performance to state-of-the-art algorithms for class-incremental learning.
Particularly for manufactured products subject to aesthetic evaluation, the industrial manufacturing process must be monitored, and visual defects detected. For this purpose, more and more computer vision-integrated inspection systems are being used. In optical inspection based on cameras or range scanners, only a few examples are typically known before novel examples are inspected. Consequently, no large data set of non-defective and defective examples could be used to train a classifier, and methods that work with limited or weak supervision must be applied. For such scenarios, I propose new data-efficient machine learning approaches based on one-class learning that reduce the need for supervision in industrial computer vision tasks. The developed novelty detection model automatically extracts features from the input images and is trained only on available non-defective reference data. On top of the feature extractor, a one-class classifier based on recent developments in deep learning is placed. I evaluate the novelty detector in an industrial inspection scenario and state-of-the-art benchmarks from the machine learning community. In the second part of this work, the model gets improved by using a small number of novel defective examples, and hence, another source of supervision gets incorporated. The targeted real-world inspection unit is based on a camera array and a flashing light illumination, allowing inline capturing of multichannel images at a high rate. Optionally, the integration of range data, such as laser or Lidar signals, is possible by using the developed targetless data fusion method.
Using multi-camera matching techniques for 3d reconstruction there is usually the trade-off between the quality of the computed depth map and the speed of the computations. Whereas high quality matching methods take several seconds to several minutes to compute a depth map for one set of images, real-time methods achieve only low quality results. In this paper we present a multi-camera matching method that runs in real-time and yields high resolution depth maps. Our method is based on a novel multi-level combination of normalized cross correlation, deformed matching windows based on the multi-level depth map information, and sub-pixel precise disparity maps. The whole process is implemented completely on the GPU. With this approach we can process four 0.7 megapixel images in 129 milliseconds to a full resolution 3d depth map. Our technique is tailored for the recognition of non-technical shapes, because our target application is face recognition.
Das Projekt eFlow, an dem unter anderem die HTWG Konstanz seit 2012 forscht, simuliert mit Hilfe einer mathematischen Simulation wie sich Menschenmassen verhalten, wenn sie ein vorgegebenes Gelände verlassen sollen. Die Simulation baut auf einen Ansatz der Finite Elemente Methode auf, in der mehrere gekoppelte Differenzialgleichungen berechnet werden müssen. Diese Berechnungen erweisen sich gerade bei komplexen Szenarien mit großem Gelände und vielen Personen als sehr rechenintensiv. Ziel dieser Bachelorarbeit ist es ein Surrogate Modell zu erstellen, welches basierend auf machine-learning Ansätzen im spezifischen auf Regressionsmethoden Ergebnisse der Simulation vorhersagen soll. Somit müssen Datensätze generiert werden. Diese entstehen durch wiederholte Durchläufe der Simulation, in der jeweils die Eingabeparameter, die in das Regressionsmodell einfließen sollen variiert werden und mit dem entsprechenden Ergebnis der Simulation verknüpft werden. Die Regressionsansätze werden dabei pro Durchlauf komplexer, in dem jeweils zusätzliche Eingabeparameter mit in die Datengenerierung aufgenommen werden. Es soll überprüft werden, ob diese Simulation mittels machine-learning Ansätzen reproduzierbar ist. Basierend auf diesen Surrogate Modellen soll es möglich gemacht werden, Situationen in Echtzeit zu überprüfen, ohne dabei den Weg der rechenaufwendigen Simulation zu gehen. Die Ergebnisse bestätigen, dass die mathematische Simulation mittels Regression reproduzierbar ist. Es erweist sich jedoch als sehr rechenaufwendig, Daten zu sammeln, um genügend Eingabeparameter mit in die Regressionsmethode einfließen zu lassen. Diese Arbeit gestaltet somit eine Vorstudie zur Umsetzung eines ausgereiften Surrogate Modells, welches jegliche Eingabeparameter der Simulation berücksichtigen kann.
Random matrices are used to filter the center of gravity (CoG) and the covariance matrix of measurements. However, these quantities do not always correspond directly to the position and the extent of the object, e.g. when a lidar sensor is used.In this paper, we propose a Gaussian processes regression model (GPRM) to predict the position and extension of the object from the filtered CoG and covariance matrix of the measurements. Training data for the GPRM are generated by a sampling method and a virtual measurement model (VMM). The VMM is a function that generates artificial measurements using ray tracing and allows us to obtain the CoG and covariance matrix that any object would cause. This enables the GPRM to be trained without real data but still be applied to real data due to the precise modeling in the VMM. The results show an accurate extension estimation as long as the reality behaves like the modeling and e.g. lidar measurements only occur on the side facing the sensor.
Motion estimation is an essential element for autonomous vessels. It is used e.g. for lidar motion compensation as well as mapping and detection tasks in a maritime environment. Because the use of gyroscopes is not reliable and a high performance inertial measurement unit is quite expensive, we present an approach for visual pitch and roll estimation that utilizes a convolutional neural network for water segmentation, a stereo system for reconstruction and simple geometry to estimate pitch and roll. The algorithm is validated on a novel, publicly available dataset recorded at Lake Constance. Our experiments show that the pitch and roll estimator provides accurate results in comparison to an Xsens IMU sensor. We can further improve the pitch and roll estimation by sensor fusion with a gyroscope. The algorithm is available in its implementation as a ROS node.
Targetless Lidar-camera registration is a repeating task in many computer vision and robotics applications and requires computing the extrinsic pose of a point cloud with respect to a camera or vice-versa. Existing methods based on learning or optimization lack either generalization capabilities or accuracy. Here, we propose a combination of pre-training and optimization using a neural network-based mutual information estimation technique (MINE [1]). This construction allows back-propagating the gradient to the calibration parameters and enables stochastic gradient descent. To ensure orthogonality constraints with respect to the rotation matrix we incorporate Lie-group techniques. Furthermore, instead of optimizing on entire images, we operate on local patches that are extracted from the temporally synchronized projected Lidar points and camera frames. Our experiments show that this technique not only improves over existing techniques in terms of accuracy, but also shows considerable generalization capabilities towards new Lidar-camera configurations.
Image novelty detection is a repeating task in computer vision and describes the detection of anomalous images based on a training dataset consisting solely of normal reference data. It has been found that, in particular, neural networks are well-suited for the task. Our approach first transforms the training and test images into ensembles of patches, which enables the assessment of mean-shifts between normal data and outliers. As mean-shifts are only detectable when the outlier ensemble and inlier distribution are spatially separate from each other, a rich feature space, such as a pre-trained neural network, needs to be chosen to represent the extracted patches. For mean-shift estimation, the Hotelling T2 test is used. The size of the patches turned out to be a crucial hyperparameter that needs additional domain knowledge about the spatial size of the expected anomalies (local vs. global). This also affects model selection and the chosen feature space, as commonly used Convolutional Neural Networks or Vision Image Transformers have very different receptive field sizes. To showcase the state-of-the-art capabilities of our approach, we compare results with classical and deep learning methods on the popular dataset CIFAR-10, and demonstrate its real-world applicability in a large-scale industrial inspection scenario using the MVTec dataset. Because of the inexpensive design, our method can be implemented by a single additional 2D-convolution and pooling layer and allows particularly fast prediction times while being very data-efficient.
Lidar sensors are widely used for environmental perception on autonomous robot vehicles (ARV). The field of view (FOV) of Lidar sensors can be reshaped by positioning plane mirrors in their vicinity. Mirror setups can especially improve the FOV for ground detection of ARVs with 2D-Lidar sensors. This paper presents an overview of several geometric designs and their strengths for certain vehicle types. Additionally, a new and easy-to-implement calibration procedure for setups of 2D-Lidar sensors with mirrors is presented to determine precise mirror orientations and positions, using a single flat calibration object with a pre-aligned simple fiducial marker. Measurement data from a prototype vehicle with a 2D-Lidar with a 2 m range using this new calibration procedure are presented. We show that the calibrated mirror orientations are accurate to less than 0.6° in this short range, which is a significant improvement over the orientation angles taken directly from the CAD. The accuracy of the point cloud data improved, and no significant decrease in distance noise was introduced. We deduced general guidelines for successful calibration setups using our method. In conclusion, a 2D-Lidar sensor and two plane mirrors calibrated with this method are a cost-effective and accurate way for robot engineers to improve the environmental perception of ARVs.
We analyse the results of a finite element simulation of a macroscopic model, which describes the movement of a crowd, that is considered as a continuum. A new formulation based on the macroscopic model from Hughes [2] is given. We present a stable numerical algorithm by approximating with a viscosity solution. The fundamental setting is given by an arbitrary domain that can contain several obstacles, several entries and must have at least one exit. All pedestrians have the goal to leave the room as quickly as possible. Nobody prefers a particular exit.
Wer schon einmal dicht gedrängt vor der Konzertbühne stand kann sich die aussichtslose Lage, wenn die Stimmung kippt und Panik aufkommt, gut vorstellen. Es ist sehr wichtig, Räume und Events, die zeitweise von sehr vielen Menschen aufgesucht werden, so zu gestalten und zu planen, dass maximale Sicherheit gewährleistet ist. Damit eine öffentliche Veranstaltung reibungslos verläuft ist eine gründliche Planung, also ein qualitativ hochwertiges Crowd Management unabdingbar.
Die Frage „Wozu braucht man das?“ vonseiten der Studierenden oder Aussagen wie „Das habe ich im Beruf später nie mehr benötigt.“ von ehemaligen Studierenden ist den meisten Mathematikdozierenden sehr vertraut. Im Projekt BiLeSA wird dem Wunsch nach Integration von Praxisnähe im Mathematikunterricht mithilfe einer Smartphone-App, welche ausgewählte Themen in der Mathematik anhand von digitalen Bildern sichtbar macht, umgesetzt. Bei den ausgewählten Themen handelt es sich um (affin) lineare Abbildungen, Ableitungen in höheren Raumdimensionen und Potenzen von Komplexen Zahlen. Die Konzeptionierung des Lernobjekts erfolgte mit dem Design Based Research (DBR) Ansatz, welches im Basisprojekt des IBH-Labs „Seamless Learning“ konzipiert und entwickelt wurde.
Interpretability and uncertainty modeling are important key factors for medical applications. Moreover, data in medicine are often available as a combination of unstructured data like images and structured predictors like patient’s metadata. While deep learning models are state-of-the-art for image classification, the models are often referred to as ’black-box’, caused by the lack of interpretability. Moreover, DL models are often yielding point predictions and are too confident about the parameter estimation and outcome predictions.
On the other side with statistical regression models, it is possible to obtain interpretable predictor effects and capture parameter and model uncertainty based on the Bayesian approach. In this thesis, a publicly available melanoma dataset, consisting of skin lesions and patient’s age, is used to predict the melanoma types by using a semi-structured model, while interpretable components and model uncertainty is quantified. For Bayesian models, transformation model-based variational inference (TM-VI) method is used to determine the posterior distribution of the parameter. Several model constellations consisting of patient’s age and/or skin lesion were implemented and evaluated. Predictive performance was shown to be best by using a combined model of image and patient’s age, while providing the interpretable posterior distribution of the regression coefficient is possible. In addition, integrating uncertainty in image and tabular parts results in larger variability of the outputs corresponding to high uncertainty of the single model components.
The main challenge in Bayesian models is to determine the posterior for the model parameters. Already, in models with only one or few parameters, the analytical posterior can only be determined in special settings. In Bayesian neural networks, variational inference is widely used to approximate difficult-to-compute posteriors by variational distributions. Usually, Gaussians are used as variational distributions (Gaussian-VI) which limits the quality of the approximation due to their limited flexibility. Transformation models on the other hand are flexible enough to fit any distribution. Here we present transformation model-based variational inference (TM-VI) and demonstrate that it allows to accurately approximate complex posteriors in models with one parameter and also works in a mean-field fashion for multi-parameter models like neural networks.
Forecasting is crucial for both system planning and operations in the energy sector. With increasing penetration of renewable energy sources, increasing fluctuations in the power generation need to be taken into account. Probabilistic load forecasting is a young, but emerging research topic focusing on the prediction of future uncertainties. However, the majority of publications so far focus on techniques like quantile regression, ensemble, or scenario-based methods, which generate discrete quantiles or sets of possible load curves. The conditioned probability distribution remains unknown and can only be estimated when the output is post-processed using a statistical method like kernel density estimation.
Instead, the proposed probabilistic deep learning model uses a cascade of transformation functions, known as normalizing flow, to model the conditioned density function from a smart meter dataset containing electricity demand information for over 4,000 buildings in Ireland. Since the whole probability density function is tractable, the parameters of the model can be obtained by minimizing the negative loglikelihood through the state of the art gradient descent. This leads to the model with the best representation of the data distribution.
Two different deep learning models have been compared, a simple three-layer fully connected neural network and a more advanced convolutional neural network for sequential data processing inspired by the WaveNet architecture. These models have been used to parametrize three different probabilistic models, a simple normal distribution, a Gaussian mixture model, and the normalizing flow model. The prediction horizon is set to one day with a resolution of 30 minutes, hence the models predict 48 conditioned probability distributions.
The normalizing flow model outperforms the two other variants for both architectures and proves its ability to capture the complex structures and dependencies causing the variations in the data. Understanding the stochastic nature of the task in such detail makes the methodology applicable for other use cases apart from forecasting. It is shown how it can be used to detect anomalies in the power grid or generate synthetic scenarios for grid planning.
Deep neural networks (DNNs) are known for their high prediction performance, especially in perceptual tasks such as object recognition or autonomous driving. Still, DNNs are prone to yield unreliable predictions when encountering completely new situations without indicating their uncertainty. Bayesian variants of DNNs (BDNNs), such as MC dropout BDNNs, do provide uncertainty measures. However, BDNNs are slow during test time because they rely on a sampling approach. Here we present a single shot MC dropout approximation that preserves the advantages of BDNNs without being slower than a DNN. Our approach is to analytically approximate for each layer in a fully connected network the expected value and the variance of the MC dropout signal. We evaluate our approach on different benchmark datasets and a simulated toy example. We demonstrate that our single shot MC dropout approximation resembles the point estimate and the uncertainty estimate of the predictive distribution that is achieved with an MC approach, while being fast enough for real-time deployments of BDNNs.
Probabilistic Deep Learning
(2020)
Probabilistic Deep Learning is a hands-on guide to the principles that support neural networks. Learn to improve network performance with the right distribution for different data types, and discover Bayesian variants that can state their own uncertainty to increase accuracy. This book provides easy-to-apply code and uses popular frameworks to keep you focused on practical applications.
At present, the majority of the proposed Deep Learning (DL) methods provide point predictions without quantifying the model's uncertainty. However, a quantification of the reliability of automated image analysis is essential, in particular in medicine when physicians rely on the results for making critical treatment decisions. In this work, we provide an entire framework to diagnose ischemic stroke patients incorporating Bayesian uncertainty into the analysis procedure. We present a Bayesian Convolutional Neural Network (CNN) yielding a probability for a stroke lesion on 2D Magnetic Resonance (MR) images with corresponding uncertainty information about the reliability of the prediction. For patient-level diagnoses, different aggregation methods are proposed and evaluated, which combine the individual image-level predictions. Those methods take advantage of the uncertainty in the image predictions and report model uncertainty at the patient-level. In a cohort of 511 patients, our Bayesian CNN achieved an accuracy of 95.33% at the image-level representing a significant improvement of 2% over a non-Bayesian counterpart. The best patient aggregation method yielded 95.89% of accuracy. Integrating uncertainty information about image predictions in aggregation models resulted in higher uncertainty measures to false patient classifications, which enabled to filter critical patient diagnoses that are supposed to be closer examined by a medical doctor. We therefore recommend using Bayesian approaches not only for improved image-level prediction and uncertainty estimation but also for the detection of uncertain aggregations at the patient-level.
Mapping of tree seedlings is useful for tasks ranging from monitoring natural succession and regeneration to effective silvicultural management. Development of methods that are both accurate and cost-effective is especially important considering the dramatic increase in tree planting that is required globally to mitigate the impacts of climate change. The combination of high-resolution imagery from unmanned aerial vehicles and object detection by convolutional neural networks (CNNs) is one promising approach. However, unbiased assessments of these models and methods to integrate them into geospatial workflows are lacking. In this study, we present a method for rapid, large-scale mapping of young conifer seedlings using CNNs applied to RGB orthomosaic imagery. Importantly, we provide an unbiased assessment of model performance by using two well-characterised trial sites together containing over 30,000 seedlings to assemble datasets with a high level of completeness. Our results showed CNN-based models trained on two sites detected seedlings with sensitivities of 99.5% and 98.8%. False positives due to tall weeds at one site and naturally regenerating seedlings of the same species led to slightly lower precision of 98.5% and 96.7%. A model trained on examples from both sites had 99.4% sensitivity and precision of 97%, showing applicability across sites. Additional testing showed that the CNN model was able to detect 68.7% of obscured seedlings missed during the initial annotation of the imagery but present in the field data. Finally, we demonstrate the potential to use a form of weakly supervised training and a tile-based processing chain to enhance the accuracy and efficiency of CNNs applied to large, high-resolution orthomosaics.