arXiv subjects

Lukas Lührs

Publications and source records attributed to Lukas Lührs.

4 recordsLinked to original sources

arXiv2026

Annot-Mix: Learning with Noisy Class Labels from Multiple Annotators via a Mixup Extension

Training with noisy class labels impairs neural networks' generalization performance. In this context, mixup is a popular regularization technique to improve training robustness by making memorizing false class labels more difficult. However, mixup neglects that multiple annotators, e.g., crowdworkers, typically provide class labels. Therefore, we propose an extension of mixup, which handles multiple class labels per instance while considering which class label originates from which annotator. Integrated into our multi-annotator classification framework annot-mix, it performs superiorly to eleven (mostly state-of-the-art) approaches in an evaluation study with eleven datasets comprising noisy class labels from either human or simulated annotators. Our code is publicly available through our GitHub repository at https://github.com/ies-research/multi-annotator-machine-learning/tree/annot-mix

cs.LG↗

arXiv2025

crowd-hpo: Realistic Hyperparameter Optimization and Benchmarking for Learning from Crowds with Noisy Labels

Crowdworking is a cost-efficient solution for acquiring class labels. Since these labels are subject to noise, various approaches to learning from crowds have been proposed. Typically, these approaches are evaluated with default hyperparameter configurations, resulting in unfair and suboptimal performance, or with hyperparameter configurations tuned via a validation set with ground truth class labels, representing an often unrealistic scenario. Moreover, both setups can produce different approach rankings, complicating study comparisons. Therefore, we introduce crowd-hpo as a framework for evaluating approaches to learning from crowds in combination with criteria to select well-performing hyperparameter configurations with access only to noisy crowd-labeled validation data. Extensive experiments with neural networks demonstrate that these criteria select hyperparameter configurations, which improve the learning from crowd approaches' generalization performances, measured on separate test sets with ground truth labels. Hence, incorporating such criteria into experimental studies is essential for enabling fairer and more realistic benchmarking.

cs.LG↗

arXiv2025

Beyond Diagonal Covariance: Flexible Posterior VAEs via Free-Form Injective Flows

Variational Autoencoders (VAEs) are powerful generative models widely used for learning interpretable latent spaces, quantifying uncertainty, and compressing data for downstream generative tasks. VAEs typically rely on diagonal Gaussian posteriors due to computational constraints. Using arguments grounded in differential geometry, we demonstrate inherent limitations in the representational capacity of diagonal covariance VAEs, as illustrated by explicit low-dimensional examples. In response, we show that a regularized variant of the recently introduced Free-form Injective Flow (FIF) can be interpreted as a VAE featuring a highly flexible, implicitly defined posterior. Crucially, this regularization yields a posterior equivalent to a full Gaussian covariance distribution, yet maintains computational costs comparable to standard diagonal covariance VAEs. Experiments on image datasets validate our approach, demonstrating that incorporating full covariance substantially improves model likelihood.

cs.LG↗

arXiv2018

Nanoporous Copper-Nickel - Macroscopic bodies of a strong and deformable nanoporous base metal by dealloying

Uniform macroscopic samples of nanoporous metal with high deformability have so far been limited to precious metals such as Au, Pd and Pt. Here we propose nanoporous Copper-Nickel (npCN) as a nanoporous base metal that can be made with mm dimensions and exhibits significant deformability. NpCN forms a uniform bicontinous network structure with feature sizes that can be controlled from 13 to 40 nm by thermal annealing. Continuous compression tests confirm ductile deformation behavior accompanied with a high strength compared to macroporous Cu- and Ni-foams with similar solid fraction.

cond-mat.mtrl-sci↗