Hot-Distance: Combining One-Hot and Signed Distance Embeddings for Segmentation

janelia7_blocks-janelia7_biblio_header | block

arXiv. 2024 Jun 25;:2406.17936. doi: 10.48550/arXiv.2406.17936

Hot-Distance: Combining One-Hot and Signed Distance Embeddings for Segmentation CellMapScientific Computing Software

Zouinkhi Marwan, Rhoades Jeff, Weigel Aubrey

janelia7_blocks-janelia7_biblio_abstract | block

Abstract

Machine learning models are only as good as the data to which they are fit. As such, it is always preferable to use as much data as possible in training models. What data can be used for fitting a model depends a lot on the formulation of the task. We introduce Hot-Distance, a novel segmentation target that incorporates the strength of signed boundary distance prediction with the flexibility of one-hot encoding, to increase the amount of usable training data for segmentation of subcellular structures in focused ion beam scanning electron microscopy (FIB-SEM).

janelia7_blocks-janelia7_biblio_authors | block

janelia7_blocks-janelia7_biblio_tools | block

Main Menu (Mobile)- Block

Main Menu - Block

Hot-Distance: Combining One-Hot and Signed Distance Embeddings for Segmentation

Abstract

Janelia Authors