Zobrazeno 1 - 10
of 1 624
pro vyhledávání: '"Ledig, A."'
This study introduces unORANIC+, a novel method that integrates unsupervised feature orthogonalization with the ability of a Vision Transformer to capture both local and global relationships for improved robustness and generalizability. The streamlin
Externí odkaz:
http://arxiv.org/abs/2409.12276
The performance of deep neural networks scales with dataset size and label quality, rendering the efficient mitigation of low-quality data annotations crucial for building robust and cost-effective systems. Existing strategies to address label noise
Externí odkaz:
http://arxiv.org/abs/2408.14358
Large and well-annotated datasets are essential for advancing deep learning applications, however often costly or impossible to obtain by a single entity. In many areas, including the medical domain, approaches relying on data sharing have become cri
Externí odkaz:
http://arxiv.org/abs/2408.00639
Despite notable advancements, the integration of deep learning (DL) techniques into impactful clinical applications, particularly in the realm of digital histopathology, has been hindered by challenges associated with achieving robust generalization
Externí odkaz:
http://arxiv.org/abs/2407.02900
The integration of neural-network-based systems into clinical practice is limited by challenges related to domain generalization and robustness. The computer vision community established benchmarks such as ImageNet-C as a fundamental prerequisite to
Externí odkaz:
http://arxiv.org/abs/2406.17536
The integration of deep learning based systems in clinical practice is often impeded by challenges rooted in limited and heterogeneous medical datasets. In addition, prioritization of marginal performance improvements on a few, narrowly scoped benchm
Externí odkaz:
http://arxiv.org/abs/2404.15786
Traditional deep learning models implicity encode knowledge limiting their transparency and ability to adapt to data changes. Yet, this adaptability is vital for addressing user data privacy concerns. We address this limitation by storing embeddings
Externí odkaz:
http://arxiv.org/abs/2402.12500
We introduce unORANIC, an unsupervised approach that uses an adapted loss function to drive the orthogonalization of anatomy and image-characteristic features. The method is versatile for diverse modalities and tasks, as it does not require domain kn
Externí odkaz:
http://arxiv.org/abs/2308.15507
Autor:
van Treeck, David, Ledig, Johannes, Scholz, Gregor, Lähnemann, Jonas, Musolino, Mattia, Tahraoui, Abbes, Brandt, Oliver, Waag, Andreas, Riechert, Henning, Geelhaar, Lutz
Publikováno v:
Beilstein J. Nanotechnol. 10, 1177 (2019)
We present the combined analysis of the electroluminescence (EL) as well as the current-voltage (I-V) behavior of single, freestanding (In,Ga)N/GaN nanowire (NW) light-emitting diodes (LEDs) in an unprocessed, self-assembled ensemble grown by molecul
Externí odkaz:
http://arxiv.org/abs/1908.08863
Autor:
Biffi, Carlo, Cerrolaza, Juan J., Tarroni, Giacomo, Bai, Wenjia, de Marvao, Antonio, Oktay, Ozan, Ledig, Christian, Folgoc, Loic Le, Kamnitsas, Konstantinos, Doumou, Georgia, Duan, Jinming, Prasad, Sanjay K., Cook, Stuart A., O'Regan, Declan P., Rueckert, Daniel
Quantification of anatomical shape changes currently relies on scalar global indexes which are largely insensitive to regional or asymmetric modifications. Accurate assessment of pathology-driven anatomical remodeling is a crucial step for the diagno
Externí odkaz:
http://arxiv.org/abs/1907.00058