arXiv subjects

Tobias Koch

Publications and source records attributed to Tobias Koch.

At least 19 recordsLinked to original sources

arXiv2026

Beyond Clear Skies: Synthetic Seasonal and Weather Variations for Real-World Drone Detection

Reliable drone detection under real-world deployment conditions requires training data that spans the full operational design domain, including adverse weather and seasonal appearance variation. However, acquiring and annotating such data at scale remains highly resource-intensive, as adverse-weather conditions are inherently difficult to control, reproduce, and sample systematically. Existing datasets therefore typically provide only limited coverage of such conditions. Conversely, synthetic data offers a scalable alternative: environmental variation becomes controllable, while modern game-engine-based pipelines provide realistic rendering and automatic annotations. Leveraging this potential, we introduce SynDroneVision-Weather (SDV-W), an systematic extension of SynDroneVision (SDV) targeting adverse-weather and seasonal domain shifts in urban drone detection. SDV-W comprises 55,187 annotated high-resolution images from three urban environments, rendered across three seasonal configurations and diverse weather conditions, including rain, snow, and fog at multiple severity levels. By preserving SDV's scene and trajectory configuration, SDV-W enables matched clean-adverse comparisons and quantification of condition-specific detector degradation. Across representative YOLO models and real-world datasets, we show that SDV-W improves detector reliability under adverse appearance shifts, reduces missed detections and false alarms, and is most effective as a complement to general-purpose synthetic drone-detection data. SDV-W will be publicly released upon paper acceptance.

cs.CV↗

arXiv2026

Detector-Augmented SAMURAI for Long-Duration Drone Tracking

Robust long-term tracking of drone is a critical requirement for modern surveillance systems, given their increasing threat potential. While detector-based approaches typically achieve strong frame-level accuracy, they often suffer from temporal inconsistencies caused by frequent detection dropouts. Despite its practical relevance, research on RGB-based drone tracking is still limited and largely reliant on conventional motion models. Meanwhile, foundation models like SAMURAI have established their effectiveness across other domains, exhibiting strong category-agnostic tracking performance. However, their applicability in drone-specific scenarios has not been investigated yet. Motivated by this gap, we present the first systematic evaluation of SAMURAI's potential for robust drone tracking in urban surveillance settings. Furthermore, we introduce a detector-augmented extension of SAMURAI to mitigate sensitivity to bounding-box initialization and sequence length. Our findings demonstrate that the proposed extension significantly improves robustness in complex urban environments, with pronounced benefits in long-duration sequences - especially under drone exit-re-entry events. The incorporation of detector cues yields consistent gains over SAMURAI's zero-shot performance across datasets and metrics, with success rate improvements of up to +0.393 and FNR reductions of up to -0.475.

cs.CV↗

arXiv2026

Simulation Code Generation for Fluid Systems using Large Language Models: Benchmarking Models and Prompting Strategies

Large language models (LLMs) have demonstrated a strong ability to generate syntactically correct code from natural-language specifications. In this study, we explore how LLMs can be harnessed to automatically translate a neutral graph representation of fluid system models into executable code for two widely adopted simulation environments: the Python library WNTR and the Modelica Standard Library. We conduct a systematic comparison of ten state-of-the-art LLMs and six prompting strategies that differ in the contextual information supplied (e.g., code or documentation). For each configuration we assess the generated code using a suite of software-quality metrics and we validate the functional fidelity of the resulting simulation models by reproducing benchmark fluid system scenarios. Our findings offer concrete guidance for researchers and engineers seeking to integrate LLM-driven code synthesis into model-based design pipelines. While the best-performing configurations achieve acceptable syntactic quality, we observe substantial gaps remain in simulation fidelity.

cs.LG↗

arXiv2026

Second-Order Asymptotics of Two-Sample Tests

In two-sampling testing, one observes two independent sequences of independent and identically distributed random variables distributed according to the distributions $P_1$ and $P_2$ and wishes to decide whether $P_1=P_2$ (null hypothesis) or $P_1\neq P_2$ (alternative hypothesis). The Gutman test for this problem compares the empirical distributions of the observed sequences and decides on the null hypothesis if the Jensen-Shannon (JS) divergence between these empirical distributions is below a given threshold. This paper proposes a generalization of the Gutman test, termed \emph{divergence test}, which replaces the JS divergence by an arbitrary divergence. For this test, the exponential decay of the type-II error probability for a fixed type-I error probability is studied. First, it is shown that the divergence test achieves the optimal first-order exponent, irrespective of the choice of divergence. Second, it is demonstrated that divergence tests with invariant divergences achieve the same second-order asymptotics as the Gutman test. In addition, a connection between two-sample testing and robust goodness-of-fit testing is established.

cs.IT↗

arXiv2026

A Converse Bound via the Nussbaum-Szkoła Mapping for Quantum Hypothesis Testing

Quantum hypothesis testing concerns the discrimination between quantum states. This paper introduces a novel lower bound for asymmetric quantum hypothesis testing that is based on the Nussbaum-Szkoła mapping. The lower bound provides a unified recovery of converse results across all major asymptotic regimes, including large-, moderate-, and small-deviations. Unlike existing bounds, which either rely on technically involved information-spectrum arguments or suffer from fixed prefactors and limited applicability in the non-asymptotic regime, the proposed bound arises from a single expression and enables, in some cases, the direct use of classical results. It is further demonstrated that the proposed bound provides accurate approximations to the optimal quantum error trade-off function at small blocklengths. Numerical comparisons with existing bounds, including those based on fidelity and information spectrum methods, highlight its improved tightness.

quant-ph↗

arXiv2026

SynDroneVision: A Synthetic Dataset for Image-Based Drone Detection

Developing robust drone detection systems is often constrained by the limited availability of large-scale annotated training data and the high costs associated with real-world data collection. However, leveraging synthetic data generated via game engine-based simulations provides a promising and cost-effective solution to overcome this issue. Therefore, we present SynDroneVision, a synthetic dataset specifically designed for RGB-based drone detection in surveillance applications. Featuring diverse backgrounds, lighting conditions, and drone models, SynDroneVision offers a comprehensive training foundation for deep learning algorithms. To evaluate the dataset's effectiveness, we perform a comparative analysis across a selection of recent YOLO detection models. Our findings demonstrate that SynDroneVision is a valuable resource for real-world data enrichment, achieving notable enhancements in model performance and robustness, while significantly reducing the time and costs of real-world data acquisition. SynDroneVision will be publicly released upon paper acceptance.

cs.CV↗

arXiv2026

Universal Outlier Hypothesis Testing via Mean- and Median-Based Tests

Universal outlier hypothesis testing refers to a hypothesis testing problem where one observes a large number of length-$n$ sequences -- the majority of which are distributed according to the typical distribution $π$ and a small number are distributed according to the outlier distribution $μ$ -- and one wishes to decide, which of these sequences are outliers without having knowledge of $π$ and $μ$. In contrast to previous works, in this paper it is assumed that both the number of observation sequences and the number of outlier sequences grow with the sequence length. In this case, the typical distribution $π$ can be estimated by computing the mean over all observation sequences, provided that the number of outlier sequences is sublinear in the total number of sequences. It is demonstrated that, in this case, one can achieve the error exponent of the maximum likelihood test that has access to both $π$ and $μ$. However, this mean-based test performs poorly when the number of outlier sequences is proportional to the total number of sequences. For this case, a median-based test is proposed that estimates $π$ as the median of all observation sequences. It is demonstrated that the median-based test achieves again the error exponent of the maximum likelihood test that has access to both $π$ and $μ$, but only with probability approaching one. To formalize this case, the typical error exponent -- similar to the typical random coding exponent introduced in the context of random coding for channel coding -- is proposed.

cs.IT↗

arXiv2025

From Engineering Diagrams to Graphs: Digitizing P&IDs with Transformers

Digitizing engineering diagrams like Piping and Instrumentation Diagrams (P&IDs) plays a vital role in maintainability and operational efficiency of process and hydraulic systems. Previous methods typically decompose the task into separate steps such as symbol detection and line detection, which can limit their ability to capture the structure in these diagrams. In this work, a transformer-based approach leveraging the Relationformer that addresses this limitation by jointly extracting symbols and their interconnections from P&IDs is introduced. To evaluate our approach and compare it to a modular digitization approach, we present the first publicly accessible benchmark dataset for P&ID digitization, annotated with graph-level ground truth. Experimental results on real-world diagrams show that our method significantly outperforms the modular baseline, achieving over 25% improvement in edge detection accuracy. This research contributes a reproducible evaluation framework and demonstrates the effectiveness of transformer models for structural understanding of complex engineering diagrams. The dataset is available under https://zenodo.org/records/14803338.

cs.CV↗

arXiv2025

On Noncoherent Multiple-Antenna Rayleigh Block-Fading Channels at Finite Blocklength

This paper investigates the maximum coding rate at which data can be transmitted over a noncoherent, multiple-input, multiple-output (MIMO) Rayleigh block-fading channel using an error-correcting code of a given blocklength with a block-error probability not exceeding a given value. A high-SNR normal approximation is derived that becomes accurate as the signal-to-noise ratio (SNR) and the number of coherence intervals over which we code tend to infinity. The obtained normal approximation complements the nonasymptotic bounds that have appeared in the literature, but whose evaluation is computationally demanding. It further lays the theoretical foundation for an analytical analysis of the fundamental tradeoff between diversity, multiplexing, and channel-estimation cost at finite blocklength and finite SNR.

cs.IT↗

arXiv2025

Fundamental Limits of Noncoherent Massive Random Access Networks

This paper studies the capacity of massive random-access cellular networks, modeled as a MIMO fading channel with an infinite number of interfering cells. To characterize the symmetric sum rate of the network, a random-coding argument is invoked together with the assumption that in all cells users draw their codebooks according to the same distribution. This can be viewed as a generalization of the assumption of Gaussian codebooks, often encountered in the literature. The network is further assumed to be noncoherent: the transmitters and receivers are cognizant of the statistics of the fading coefficients, but are ignorant of their realizations. Finally, it is assumed that the users access the network at random. For the considered channel model, rigorous bounds on the capacity are derived. The behavior of these bounds depends critically on the path loss from signals transmitted in interfering cells to the intended cell. In particular, if the fading coefficients of the interferers (ordered according to their distance to the receiver) decay exponentially or more slowly, then the capacity is bounded in the transmit power. This confirms that the saturation regime in interference-limited networks -- observed by Lozano, Heath, and Andrews ("Fundamental limits of cooperation", IEEE Trans. Inf. Theory, Sept. 2013) -- cannot be avoided by random user activity or by using channel inputs beyond the scale family. In contrast, if the fading coefficients decay faster than double-exponentially, then the capacity is unbounded in the transmit power. Proving an unbounded capacity is nontrivial even if the number of interfering cells is finite, since the condition that the users' codebooks follow the same distribution prevents interference-avoiding strategies such as time- or frequency-division multiple access. We obtain this result by using bursty signaling together with treating interference as noise.

cs.IT↗

arXiv2025

Performance Optimization of YOLO-FEDER FusionNet for Robust Drone Detection in Visually Complex Environments

Drone detection in visually complex environments remains challenging due to background clutter, small object scale, and camouflage effects. While generic object detectors like YOLO exhibit strong performance in low-texture scenes, their effectiveness degrades in cluttered environments with low object-background separability. To address these limitations, this work presents an enhanced iteration of YOLO-FEDER FusionNet -- a detection framework that integrates generic object detection with camouflage object detection techniques. Building upon the original architecture, the proposed iteration introduces systematic advancements in training data composition, feature fusion strategies, and backbone design. Specifically, the training process leverages large-scale, photo-realistic synthetic data, complemented by a small set of real-world samples, to enhance robustness under visually complex conditions. The contribution of intermediate multi-scale FEDER features is systematically evaluated, and detection performance is comprehensively benchmarked across multiple YOLO-based backbone configurations. Empirical results indicate that integrating intermediate FEDER features, in combination with backbone upgrades, contributes to notable performance improvements. In the most promising configuration -- YOLO-FEDER FusionNet with a YOLOv8l backbone and FEDER features derived from the DWD module -- these enhancements lead to a FNR reduction of up to 39.1 percentage points and a mAP increase of up to 62.8 percentage points at an IoU threshold of 0.5, compared to the initial baseline.

cs.CV↗

arXiv2025

Rotation Invariance in Floor Plan Digitization using Zernike Moments

Nowadays, a lot of old floor plans exist in printed form or are stored as scanned raster images. Slight rotations or shifts may occur during scanning. Bringing floor plans of this form into a machine readable form to enable further use, still poses a problem. Therefore, we propose an end-to-end pipeline that pre-processes the image and leverages a novel approach to create a region adjacency graph (RAG) from the pre-processed image and predict its nodes. By incorporating normalization steps into the RAG feature extraction, we significantly improved the rotation invariance of the RAG feature calculation. Moreover, applying our method leads to an improved F1 score and IoU on rotated data. Furthermore, we proposed a wall splitting algorithm for partitioning walls into segments associated with the corresponding rooms.

cs.CV↗

arXiv2024

Quasi Monolithic Fiber Collimators

Interferometric displacement measurements, especially in space interferometry applications, face challenges from thermal expansion. Bonded assemblies of ultra-low thermal expansion glass-ceramics offer a solution; however, transitioning from light transport in fibers to free beam propagation presents a notable challenge. These experiments often need an interface to convert between laser beams propagating through fiber optics into a well-defined free beam and vice versa. These interfaces must also be made of rigid glass pieces that can be bonded to a glass base plate. Current designs for these fiber collimators, often called fiber injector optical sub-assemblies, require multiple glass parts fabricated to very tight tolerances and assembled with special alignment tools. We present a simplified quasi-monolithic fiber collimator that can generate a well-collimated laser beam. The complexity and tolerances of bonding are reduced by combining the alignment of the fiber mode to the imaging lens in one step with active mode control: the welding of the fiber to the glass body. We produce several of these designs and test that the desired light field is achieved, its profile is described as a Gaussian beam, and the beam-pointing stability is acceptable for such a piece. In each case, they perform at least as well as a standard commercial fiber collimator. These Quasi Monolithic Fiber Collimators offer a promising and easy-to-implement solution to convert between free beam and fiber-coupled lasers in experiments sensitive to long term thermal drifts.

physics.optics↗

arXiv2024

YOLO-FEDER FusionNet: A Novel Deep Learning Architecture for Drone Detection

Predominant methods for image-based drone detection frequently rely on employing generic object detection algorithms like YOLOv5. While proficient in identifying drones against homogeneous backgrounds, these algorithms often struggle in complex, highly textured environments. In such scenarios, drones seamlessly integrate into the background, creating camouflage effects that adversely affect the detection quality. To address this issue, we introduce a novel deep learning architecture called YOLO-FEDER FusionNet. Unlike conventional approaches, YOLO-FEDER FusionNet combines generic object detection methods with the specialized strength of camouflage object detection techniques to enhance drone detection capabilities. Comprehensive evaluations of YOLO-FEDER FusionNet show the efficiency of the proposed model and demonstrate substantial improvements in both reducing missed detections and false alarms.

cs.CV↗

arXiv2024

On the Second-Order Asymptotics of the Hoeffding Test and Other Divergence Tests

Consider a binary statistical hypothesis testing problem, where $n$ independent and identically distributed random variables $Z^n$ are either distributed according to the null hypothesis $P$ or the alternative hypothesis $Q$, and only $P$ is known. A well-known test that is suitable for this case is the so-called Hoeffding test, which accepts $P$ if the Kullback-Leibler (KL) divergence between the empirical distribution of $Z^n$ and $P$ is below some threshold. This work characterizes the first and second-order terms of the type-II error probability for a fixed type-I error probability for the Hoeffding test as well as for divergence tests, where the KL divergence is replaced by a general divergence. It is demonstrated that, irrespective of the divergence, divergence tests achieve the first-order term of the Neyman-Pearson test, which is the optimal test when both $P$ and $Q$ are known. In contrast, the second-order term of divergence tests is strictly worse than that of the Neyman-Pearson test. It is further demonstrated that divergence tests with an invariant divergence achieve the same second-order term as the Hoeffding test, but divergence tests with a non-invariant divergence may outperform the Hoeffding test for some alternative hypotheses $Q$. Potentially, this behavior could be exploited by a composite hypothesis test with partial knowledge of the alternative hypothesis $Q$ by tailoring the divergence of the divergence test to the set of possible alternative hypotheses.

cs.IT↗

arXiv2023

LORD: Leveraging Open-Set Recognition with Unknown Data

Handling entirely unknown data is a challenge for any deployed classifier. Classification models are typically trained on a static pre-defined dataset and are kept in the dark for the open unassigned feature space. As a result, they struggle to deal with out-of-distribution data during inference. Addressing this task on the class-level is termed open-set recognition (OSR). However, most OSR methods are inherently limited, as they train closed-set classifiers and only adapt the downstream predictions to OSR. This work presents LORD, a framework to Leverage Open-set Recognition by exploiting unknown Data. LORD explicitly models open space during classifier training and provides a systematic evaluation for such approaches. We identify three model-agnostic training strategies that exploit background data and applied them to well-established classifiers. Due to LORD's extensive evaluation protocol, we consistently demonstrate improved recognition of unknown data. The benchmarks facilitate in-depth analysis across various requirement levels. To mitigate dependency on extensive and costly background datasets, we explore mixup as an off-the-shelf data generation technique. Our experiments highlight mixup's effectiveness as a substitute for background datasets. Lightweight constraints on mixup synthesis further improve OSR performance.

cs.CV↗

arXiv2022

Exploring the Open World Using Incremental Extreme Value Machines

Dynamic environments require adaptive applications. One particular machine learning problem in dynamic environments is open world recognition. It characterizes a continuously changing domain where only some classes are seen in one batch of the training data and such batches can only be learned incrementally. Open world recognition is a demanding task that is, to the best of our knowledge, addressed by only a few methods. This work introduces a modification of the widely known Extreme Value Machine (EVM) to enable open world recognition. Our proposed method extends the EVM with a partial model fitting function by neglecting unaffected space during an update. This reduces the training time by a factor of 28. In addition, we provide a modified model reduction using weighted maximum K-set cover to strictly bound the model complexity and reduce the computational effort by a factor of 3.5 from 2.1 s to 0.6 s. In our experiments, we rigorously evaluate openness with two novel evaluation protocols. The proposed method achieves superior accuracy of about 12 % and computational efficiency in the tasks of image classification and face recognition.

cs.LG↗

arXiv2022

Second-Order Asymptotics of Hoeffding-Like Hypothesis Tests

We consider a binary statistical hypothesis testing problem, where $n$ independent and identically distributed random variables $Z^n$ are either distributed according to the null hypothesis $P$ or the alternate hypothesis $Q$, and only $P$ is known. For this problem, a well-known test is the Hoeffding test, which accepts $P$ if the Kullback-Leibler (KL) divergence between the empirical distribution of $Z^n$ and $P$ is below some threshold. In this paper, we consider Hoeffding-like tests, where the KL divergence is replaced by other divergences, and characterize, for a large class of divergences, the first and second-order terms of the type-II error for a fixed type-I error. Since the considered class includes the KL divergence, we obtain the second-order term of the Hoeffiding test as a special case.

cs.IT↗