Zobrazeno 1 - 10
of 1 983
pro vyhledávání: '"A. Duffner"'
Publikováno v:
Medical Image Analysis, 2024, 97, pp.103270
Recently, federated learning has raised increasing interest in the medical image analysis field due to its ability to aggregate multi-center data with privacy-preserving properties. A large amount of federated training schemes have been published, wh
Externí odkaz:
http://arxiv.org/abs/2410.17265
Publikováno v:
Machine Learning and Knowledge Discovery in Databases. Research Track (ECML PKDD 2024), Sep 2024, Vilnius, Lithuania. pp.369-385
Empirical studies show that federated learning exhibits convergence issues in Non Independent and Identically Distributed (IID) setups. However, these studies only focus on label distribution shifts, or concept shifts (e.g. ambiguous tasks). In this
Externí odkaz:
http://arxiv.org/abs/2410.14693
Monocular depth estimation has greatly improved in the recent years but models predicting metric depth still struggle to generalize across diverse camera poses and datasets. While recent supervised methods mitigate this issue by leveraging ground pri
Externí odkaz:
http://arxiv.org/abs/2409.14850
GNNs are powerful models based on node representation learning that perform particularly well in many machine learning problems related to graphs. The major obstacle to the deployment of GNNs is mostly a problem of societal acceptability and trustwor
Externí odkaz:
http://arxiv.org/abs/2406.11594
Autor:
Brandao, Eduardo, Nakhoul, Anthony, Duffner, Stefan, Emonet, Rémi, Garrelie, Florence, Habrard, Amaury, Jacquenet, François, Pigeon, Florent, Sebban, Marc, Colombier, Jean-Philippe
Publikováno v:
Physical Review Letters 130.22 (2023): 226201
Ultrafast laser irradiation can induce spontaneous self-organization of surfaces into dissipative structures with nanoscale reliefs. These surface patterns emerge from symmetry-breaking dynamical processes that occur in Rayleigh-B\'enard-like instabi
Externí odkaz:
http://arxiv.org/abs/2310.13453
Federated learning and its application to medical image segmentation have recently become a popular research topic. This training paradigm suffers from statistical heterogeneity between participating institutions' local datasets, incurring convergenc
Externí odkaz:
http://arxiv.org/abs/2310.11480
Publikováno v:
Document Analysis and Recognition ICDAR 2023 Workshops pages 47 to 64
Since their release, Transformers have revolutionized many fields from Natural Language Understanding to Computer Vision. Document Understanding (DU) was not left behind with first Transformer based models for DU dating from late 2019. However, the c
Externí odkaz:
http://arxiv.org/abs/2309.05503
Publikováno v:
Document Analysis Systems (DAS) 2022 pages 111 to 125
Transformer-based Language Models are widely used in Natural Language Processing related tasks. Thanks to their pre-training, they have been successfully adapted to Information Extraction in business documents. However, most pre-training tasks propos
Externí odkaz:
http://arxiv.org/abs/2309.05429
Autor:
C. Hugenschmidt, J. Ingwersen, W. Sangchan, Y. Sukvanachaikul, A. Duffner, S. Uhlenbrook, T. Streck
Publikováno v:
Hydrology and Earth System Sciences, Vol 18, Iss 2, Pp 525-537 (2014)
Land-use change in the mountainous parts of northern Thailand is reflected by an increased application of agrochemicals, which may be lost to surface and groundwater. The close relation between flow paths and contaminant transport within hydrological
Externí odkaz:
https://doaj.org/article/deb3962a08bd48edb5e796cf57dc5fb7
Publikováno v:
IEEE Transactions on Neural Networks and Learning Systems, v. 29, n. 12, Dec. 2018
In this paper, we present an approach for minimizing the computational complexity of trained Convolutional Neural Networks (ConvNet). The idea is to approximate all elements of a given ConvNet and replace the original convolutional filters and parame
Externí odkaz:
http://arxiv.org/abs/2208.00087