Bookmark Saya

arXiv Open Access 2022

Panoptic segmentation with highly imbalanced semantic labels

Josef Lorenz Rumberger Elias Baumann Peter Hirsch Andrew Janowczyk Inti Zlobec +1 lainnya
Lihat Sumber

Abstrak

We describe here the panoptic segmentation method we devised for our participation in the CoNIC: Colon Nuclei Identification and Counting Challenge at ISBI 2022. Key features of our method are a weighted loss specifically engineered for semantic segmentation of highly imbalanced cell types, and a state-of-the art nuclei instance segmentation model, which we combine in a Hovernet-like architecture.

Topik & Kata Kunci

eess.IV cs.CV

Penulis (6)

J

Josef Lorenz Rumberger

E

Elias Baumann

P

Peter Hirsch

A

Andrew Janowczyk

I

Inti Zlobec

D

Dagmar Kainmueller

Format Sitasi

APA MLA BibTeX
Rumberger, J.L., Baumann, E., Hirsch, P., Janowczyk, A., Zlobec, I., Kainmueller, D. (2022). Panoptic segmentation with highly imbalanced semantic labels. https://arxiv.org/abs/2203.11692

Akses Cepat

Lihat di Sumber
Informasi Jurnal
Tahun Terbit
2022
Bahasa
en
Sumber Database
arXiv
Akses
Open Access ✓