Zobrazeno 1 - 10
of 284
pro vyhledávání: '"Müller Maximilian"'
Autor:
Mueller, Maximilian, Hein, Matthias
In realistic medical settings, the data are often inherently long-tailed, with most samples concentrated in a few classes and a long tail of rare classes, usually containing just a few samples. This distribution presents a significant challenge becau
Externí odkaz:
http://arxiv.org/abs/2409.01317
Autor:
Mueller, Maximilian, Hein, Matthias
VisionTransformers have been shown to be powerful out-of-distribution detectors for ImageNet-scale settings when finetuned from publicly available checkpoints, often outperforming other model types on popular benchmarks. In this work, we investigate
Externí odkaz:
http://arxiv.org/abs/2405.17447
Autor:
Rodighiero, Dario, Derry, Lins, Duhaime, Douglas, Kruguer, Jordan, Mueller, Maximilian C., Pietsch, Christopher, Schnapp, Jeffrey T., Steward, Jeff
Publikováno v:
IDJ 27 (1): 21-34 (2022)
Surprise Machines is a project of experimental museology that sets out to visualize the entire image collection of the Harvard Art Museums, intending to open up unexpected vistas on more than 200,000 objects usually inaccessible to visitors. Part of
Externí odkaz:
http://arxiv.org/abs/2308.09343
Sharpness-aware minimization (SAM) was proposed to reduce sharpness of minima and has been shown to enhance generalization performance in various settings. In this work we show that perturbing only the affine normalization parameters (typically compr
Externí odkaz:
http://arxiv.org/abs/2306.04226
Out-of-distribution (OOD) detection is the problem of identifying inputs which are unrelated to the in-distribution task. The OOD detection performance when the in-distribution (ID) is ImageNet-1K is commonly being tested on a small range of test OOD
Externí odkaz:
http://arxiv.org/abs/2306.00826
Autor:
Andriushchenko, Maksym, Croce, Francesco, Müller, Maximilian, Hein, Matthias, Flammarion, Nicolas
Sharpness of minima is a promising quantity that can correlate with generalization in deep networks and, when optimized during training, can improve generalization. However, standard sharpness is not invariant under reparametrizations of neural netwo
Externí odkaz:
http://arxiv.org/abs/2302.07011
Publikováno v:
EPJ Web of Conferences, Vol 203, p 01008 (2019)
The determination of the current driven by electron cyclotron waves is usually performed employing ray/beam tracing codes, which require as an input the magnetic equilibrium, the electron density and the electron temperature profiles on one side and
Externí odkaz:
https://doaj.org/article/f44e0c495d2d4ca78a6301562575a8f7
Autor:
Jacob, Martin1 (AUTHOR) martin.jacob@whu.edu, Müller, Maximilian A.2 (AUTHOR), Wulff, Thorben1 (AUTHOR)
Publikováno v:
Contemporary Accounting Research. Winter2023, Vol. 40 Issue 4, p2785-2815. 31p.
Publikováno v:
MATEC Web of Conferences, Vol 233, p 00020 (2018)
An important element of the process of aircraft certification is the demonstration of the crashworthiness of the structure in the event of an emergency landing on water, also referred to as ditching. Novel numerical simulation methods that incorporat
Externí odkaz:
https://doaj.org/article/a1e8277225404854882701260f2a12f0
We investigate uncertainty estimation and multimodality via the non-deterministic predictions of Bayesian neural networks (BNNs) in fluid simulations. To this end, we deploy BNNs in three challenging experimental test-cases of increasing complexity:
Externí odkaz:
http://arxiv.org/abs/2205.01222