Metadata Improves Segmentation Through Multitasking Elicitation

Autor:	Plutenko, Iaroslav, Papkov, Mikhail, Palo, Kaupo, Parts, Leopold, Fishman, Dmytro
Rok vydání:	2023
Předmět:	Electrical Engineering and Systems Science - Image and Video Processing Computer Science - Computer Vision and Pattern Recognition Computer Science - Machine Learning
Druh dokumentu:	Working Paper
Popis:	Metainformation is a common companion to biomedical images. However, this potentially powerful additional source of signal from image acquisition has had limited use in deep learning methods, for semantic segmentation in particular. Here, we incorporate metadata by employing a channel modulation mechanism in convolutional networks and study its effect on semantic segmentation tasks. We demonstrate that metadata as additional input to a convolutional network can improve segmentation results while being inexpensive in implementation as a nimble add-on to popular models. We hypothesize that this benefit of metadata can be attributed to facilitating multitask switching. This aspect of metadata-driven systems is explored and discussed in detail. Comment: Accepted for DART @ MICCAI 2023
Databáze:	arXiv
Externí odkaz:	http://arxiv.org/abs/2308.09411 Zobrazit plný text záznamu View this record from Arxiv