Panoptic segmentation with highly imbalanced semantic labels

Josef Lorenz Rumberger, Elias Baumann, Peter Hirsch, Dagmar Kainmueller

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.