Can I read Training a Universal Instance Segmentation Network for Live Cell Images of Various Cell Types and Imaging Modalities on EtoBox?

Training a Universal Instance Segmentation Network for Live Cell Images of Various Cell Types and Imaging Modalities by Guo, Tianqi; Wang, Yin; Solorio, Luis; Allebach, Jan P. is a scholarly article available to read on EtoBox.

What is Training a Universal Instance Segmentation Network for Live Cell Images of Various Cell Types and Imaging Modalities about?

We share our recent findings in an attempt to train a universal segmentation network for various cell types and imaging modalities. Our method was built on the generalized U-Net architecture, which allows the evaluation of each component individually. We modified the traditional binary training targets to include three classes for direct instance segmentation. Detailed experiments were performed regarding training schemes, training settings, network backbones, and individual modules on the segmentation performance. Our proposed training scheme draws minibatches in turn from each dataset, and the gradients are accumulated before an optimization step. We found that the key to training a universal network is all-time supervision on all datasets, and it is necessary to sample each dataset in an unbiased way. Our experiments also suggest that there might exist common features to define cell boundaries across cell types and imaging modalities, which could allow application of trained models to totally unseen datasets. A few training tricks can further boost the segmentation performance, including uneven class weights in the cross-entropy loss function, well-designed learning rate schedul

Author

Guo, Tianqi; Wang, Yin; Solorio, Luis; Allebach, Jan P.

Published

2022

Language

EN