arXiv subjects

Franz Klein

Publications and source records attributed to Franz Klein.

4 recordsLinked to original sources

arXiv2026

QFireNet: A Quantum-Enhanced U-Net for Wildfire Segmentation from Sentinel-2 Imagery

Wildfire detection from satellite imagery is a semantic image segmentation problem that has proven to be difficult due to challenges such as class imbalance, feature complexity, and atmospheric interference. In this paper, we build on the foundational U-Net image segmentation model to develop a quantum-hybrid solution in hopes of more effectively modeling the high-dimensional spectral feature space of the Sen2Fire dataset. We inject a variational quantum circuit in the bottleneck portion of U-Net, specifically the QuFeX and QB-Net ansatzes. We test a classical Feature Pyramid Network (FPN) for further comparative analysis of the model, and we also explore classical improvements to the U-Net model and its training process, including a compression of parameters, alternative loss functions, and uniform mixing of input data. Our primary finding is that under matched conditions, both QB-Net (with an $F_1$ score of 31.18) and QuFeX ($F_1 = 30.79$) outperformed the classical U-Net baseline results ($F_1 = 28.71$). Additionally, the classical FPN achieved a comparable score of 31.13. A crucial finding was that data mixing removed a significant domain shift between the geographically-separated train and test sets, which boosted the classical FPN $F_1$ score to 39.76. We validate the architecture's robustness and generalizability to the wildfire detection problem via cross-dataset transfer on the California Burned Areas (CaBuAr) dataset. Overall, we find that quantum machine learning has potential to provide an advantage in the problem of wildfire image segmentation, and further experiments will continue to validate and expand upon this finding.

cs.LG↗

arXiv2026

Quantum error correction and biological error correction: A structural analogy between qubits and neurons

We draw a structural analogy between quantum error correction (QEC) and error handling in neural circuits with respect to their redundant encodings and constraint-based inferences. In QEC, logical information is embedded in a protected codespace within a larger Hilbert space. A set of commuting checks (e.g. stabilizer constraints) is repeatedly evaluated to produce an error syndrome that identifies which constraints were violated without directly revealing the logical state. A decoder then maps the syndrome to a recovery operation that returns the system to the codespace and suppresses logical failure below a threshold. Neural circuits exhibit error-control strategies that can be viewed through a related biological error correction (BEC) pattern: information is distributed across multiple neurons (redundant encoding), yielding reliable collective activity from error-prone unit operations of individual neurons. The structural analogy with QEC raises the question whether collective activity may be constrained on lower-dimensional manifolds (a biological codespace), allowing recurrent circuit dynamics and mismatch signals to function as syndrome-like indicators of constraint violations, driving fast corrective dynamics and slower adaptive updates. Our structural analogy also suggests that new insights into brain-inspired algorithms for collective information processing may inform novel QEC approaches. We perform numerical experiments using simplified models of qubit and neuron dynamics to illustrate the analogy.

physics.bio-ph↗

arXiv2022

Diverse Image Captioning with Grounded Style

Stylized image captioning as presented in prior work aims to generate captions that reflect characteristics beyond a factual description of the scene composition, such as sentiments. Such prior work relies on given sentiment identifiers, which are used to express a certain global style in the caption, e.g. positive or negative, however without taking into account the stylistic content of the visual scene. To address this shortcoming, we first analyze the limitations of current stylized captioning datasets and propose COCO attribute-based augmentations to obtain varied stylized captions from COCO annotations. Furthermore, we encode the stylized information in the latent space of a Variational Autoencoder; specifically, we leverage extracted image attributes to explicitly structure its sequential latent space according to different localized style characteristics. Our experiments on the Senticap and COCO datasets show the ability of our approach to generate accurate captions with diversity in styles that are grounded in the image.

cs.CV↗

arXiv2012

Measurement of the generalized form factors near threshold via $γ^* p \to nπ^+$ at high $Q^2$

We report the first extraction of the pion-nucleon multipoles near the production threshold for the $nπ^+$ channel at relatively high momentum transfer ($Q^2$ up to 4.2 $\rm{GeV^2}$). The dominance of the s-wave transverse multipole ($E_{0+}$), expected in this region, allowed us to access the generalized form factor $G_1$ within the light-cone sum rule (LCSR) framework as well as the axial form factor $G_A$. The data analyzed in this work were collected by the nearly $4π$ CEBAF Large Acceptance Spectrometer (CLAS) using a 5.754 $\rm{GeV}$ electron beam on a proton target. The differential cross section and the $π-N$-multipole $E_{0+}/G_D$ were measured using two different methods, the LCSR and a direct multipole fit. The results from the two methods are found to be consistent and almost $Q^2$ independent.

nucl-ex↗