arXiv subjects

Christian Schön

Publications and source records attributed to Christian Schön.

5 recordsLinked to original sources

arXiv2026

Bounding Box Label Propagation for Re-Annotation of Document Layout Analysis Datasets

Datasets in practical document processing scenarios typically grow over time, and their class annotations undergo continuous refinement. This creates significant re-annotation efforts, which are time-consuming and costly. A promising remedy is to re-annotate only a small subset of available documents manually and apply semi-supervised learning techniques that leverage both labelled and unlabelled data. Although there are numerous approaches to tackle this problem for classification, there exists no adaptation for the problem of re-classifying object detection instances, e.g. for document layout analysis. To this end, we propose Bounding Box Label Propagation (BBLP), a pseudo-labelling framework for object detection. An object encoder integrates visual, textual, and positional embeddings from object detection samples to come up with a joint embedding that can be used for Label Propagation on partially annotated datasets in a plug-and-play fashion. Evaluation results indicate that the proposed approach produces high-quality class annotations of bounding boxes. In the D4LA layout analysis dataset, it achieves a mAP of 54.0%, corresponding to 81.6% of fully supervised performance, while using only 10% labelled data. Our work demonstrates the potential of Label Propagation for object detection and lays the groundwork for reducing manual annotation efforts in real-world document processing applications.

cs.CV↗

arXiv2023

Surface reconstruction induced anisotropic energy landscape of bismuth monomers and dimers on the Si(001) surface

Spin qubits have attracted tremendous attention in the effort of building quantum computers over the years. Natural atomic scale candidates are group-V dopants in silicon, not only showing ultra-long lifetimes but also being compatible with current semiconductor technology. Nevertheless, bulk dopants are difficult to move with atomic precision, impeding the realization of desired structures for quantum computing. A solution is to place the atom on the surface which opens possibilities for atom level manipulations using scanning tunneling microscopy (STM). For this purpose, bismuth appears to be a good candidate. Here, we use ab-initio methods to study theoretically the adsorption of bismuth atoms on the Si(001) surface and investigate the adsorption sites and the transitions between them. We demonstrate the complex influence of the dimer row surface reconstruction on the energy landscape seen by a bismuth monomer and a dimer on the surface, and find anisotropic transition paths for movement on the surface. From a deposition simulation we obtain the expected occupation of adsorption sites. Our work lays the foundation for further application of bismuth atoms as qubits on silicon surfaces.

cond-mat.mes-hall↗

arXiv2021

There is No Such Thing as an "Index"! or: The next 500 Indexing Papers

Index structures are a building block of query processing and computer science in general. Since the dawn of computer technology there have been index structures. And since then, a myriad of index structures are being invented and published each and every year. In this paper we argue that the very idea of "inventing an index" is a misleading concept in the first place. It is the analogue of "inventing a physical query plan". This paper is a paradigm shift in which we propose to drop the idea to handcraft index structures (as done for binary search trees over B-trees to any form of learned index) altogether. We present a new automatic index breeding framework coined Genetic Generic Generation of Index Structures (GENE). It is based on the observation that almost all index structures are assembled along three principal dimensions: (1) structural building blocks, e.g., a B-tree is assembled from two different structural node types (inner and leaf nodes), (2) a couple of invariants, e.g., for a B-tree all paths have the same length, and (3) decisions on the internal layout of nodes (row or column layout, etc.). We propose a generic indexing framework that can mimic many existing index structures along those dimensions. Based on that framework we propose a generic genetic index generation algorithm that, given a workload and an optimization goal, can automatically assemble and mutate, in other words 'breed' new index structure 'species'. In our experiments we follow multiple goals. We reexamine some good old wisdom from database technology. Given a specific workload, will GENE even breed an index that is equivalent to what our textbooks and papers currently recommend for such a workload? Or can we do even more? Our initial results strongly indicate that generated indexes are the next step in designing index structures.

cs.DB↗

arXiv2019

Make Thunderbolts Less Frightening -- Predicting Extreme Weather Using Deep Learning

Forecasting severe weather conditions is still a very challenging and computationally expensive task due to the enormous amount of data and the complexity of the underlying physics. Machine learning approaches and especially deep learning have however shown huge improvements in many research areas dealing with large datasets in recent years. In this work, we tackle one specific sub-problem of weather forecasting, namely the prediction of thunderstorms and lightning. We propose the use of a convolutional neural network architecture inspired by UNet++ and ResNet to predict thunderstorms as a binary classification problem based on satellite images and lightnings recorded in the past. We achieve a probability of detection of more than 94% for lightnings within the next 15 minutes while at the same time minimizing the false alarm ratio compared to previous approaches.

cs.LG↗

arXiv2019

The Error is the Feature: how to Forecast Lightning using a Model Prediction Error

Despite the progress within the last decades, weather forecasting is still a challenging and computationally expensive task. Current satellite-based approaches to predict thunderstorms are usually based on the analysis of the observed brightness temperatures in different spectral channels and emit a warning if a critical threshold is reached. Recent progress in data science however demonstrates that machine learning can be successfully applied to many research fields in science, especially in areas dealing with large datasets. We therefore present a new approach to the problem of predicting thunderstorms based on machine learning. The core idea of our work is to use the error of two-dimensional optical flow algorithms applied to images of meteorological satellites as a feature for machine learning models. We interpret that optical flow error as an indication of convection potentially leading to thunderstorms and lightning. To factor in spatial proximity we use various manual convolution steps. We also consider effects such as the time of day or the geographic location. We train different tree classifier models as well as a neural network to predict lightning within the next few hours (called nowcasting in meteorology) based on these features. In our evaluation section we compare the predictive power of the different models and the impact of different features on the classification result. Our results show a high accuracy of 96% for predictions over the next 15 minutes which slightly decreases with increasing forecast period but still remains above 83% for forecasts of up to five hours. The high false positive rate of nearly 6% however needs further investigation to allow for an operational use of our approach.

cs.LG↗