The reviewed record of science sign in
Pith

arxiv: 2203.11692 · v4 · pith:EXDMYSTN · submitted 2022-03-03 · eess.IV · cs.CV

Panoptic segmentation with highly imbalanced semantic labels

Reviewed by Pith T0 review T1 audit T2 compute T3 formal T4 kernel pith:EXDMYSTNrecord.jsonopen to challenge →

classification eess.IV cs.CV
keywords segmentationhighlyimbalancedmethodnucleipanopticsemanticarchitecture
0
0 comments X
read the original abstract

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.

This paper has not been read by Pith yet.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.