Pascal Kaiser

TL;DR: Can training with large-scale publicly available labels replace a substantial part of the manual labeling effort and still achieve sufficient performance and can satisfying performance can be obtained with significantly less manual annotation effort?

TL;DR: In this article, a state-of-the-art CNN architecture was proposed for semantic segmentation of buildings and roads in aerial images, and compared with different training data sets, ranging from manually labeled ground truth of the same city to automatic training data derived from OpenStreetMap data from distant locations.

TL;DR: It is found that the female components of the SI system, including SRK and the female downstream signaling pathway, are still functional in these accessions, suggesting that the degradation of male components was responsible for the loss of SI in allotetraploid Arabidopsis kamchatica.

TL;DR: The proposed deep learning segmentation algorithm (CNN) for automated eye compartment segmentation in OCT B-scans (SDOCT and SSOCT) is on par with manual segmentations by human graders.

TL;DR: In this paper, a Traceable Relevance Explainability (T-REX) technique was used for optical coherence tomography image segmentation, which is based on ground truth generation by multiple graders, calculation of Hamming distances among graders and the machine learning algorithm, as well as a smart data visualization.