J
Jiří Borovec
Researcher at Czech Technical University in Prague
Publications - 5
Citations - 68
Jiří Borovec is an academic researcher from Czech Technical University in Prague. The author has contributed to research in topics: Image segmentation & Cut. The author has an hindex of 3, co-authored 4 publications receiving 28 citations.
Papers
More filters
Journal ArticleDOI
TorchMetrics - Measuring Reproducibility in PyTorch
Nicki Skafte Detlefsen,Jiří Borovec,Justus Schock,Ananya Harsh Jha,Thomas Edward Koker,Luca Di Liello,Daniel Štancl,Changsheng Quan,Maxim Grechkin,William Falcon +9 more
TL;DR: A main problem with reproducing machine learning publications is the variance of metric implementations across papers, where a lack of standardization leads to different behavior in mechanisms such as checkpointing, learning rate schedulers or early stopping.
Journal ArticleDOI
Supervised and unsupervised segmentation using superpixels, model estimation, and graph cut
TL;DR: A fast and general multiclass image segmentation method consisting of a computation of superpixels, extraction of superpixel-based descriptors, and calculating image-based class probabilities in a supervised or unsupervised manner that outperform the baseline results.
Journal ArticleDOI
Region growing using superpixels with learned shape prior
TL;DR: The performance of the proposed method is demonstrated and it is compared with alternative approaches on the task of segmenting individual eggs in microscopy images of Drosophila ovaries on the level of superpixels instead of pixels.
Book ChapterDOI
Binary Pattern Dictionary Learning for Gene Expression Representation in Drosophila Imaginal Discs
Jiří Borovec,Jan Kybic +1 more
TL;DR: This work presents an image processing pipeline which accepts a large number of images, containing spatial expression information for thousands of genes in Drosophila imaginal discs, and describes the preprocessing phase, where input images are segmented to recover the activation images and spatially aligned to a common reference.
Book ChapterDOI
Detection and Localization of Drosophila Egg Chambers in Microscopy Images
TL;DR: An image processing pipeline to detect and localize Drosophila egg chambers that is able to detect 96% of human-expert annotated egg chambers at relevant developmental stages with less than 1% false-positive rate, which is adequate for the further analysis.