Great new work by Jonah Kan Thomas Marini Galen Brennan Tim Baran et al URMC Imaging ECE at University of Rochester University of Rochester - 'WATUNet: a deep #neuralnetwork for segmentation of volumetric sweep #imaging #ultrasound' - iopscience.iop.org/article/10.108… #machinelearning #radiology #cancer #oncology #health

WATUNet: a deep neural network for segmentation of volumetric sweep imaging ultrasound doi.org/10.1088/2632-2… via Machine Learning: Science and Technology

A short thread about changes in the transformer architecture since 2017. Reading articles about LLMs, you can see phrases like “we use a standard transformer architecture.” But what does "standard" mean, and have there been changes since the original article? (1/6)

One of the biggest bottlenecks in deploying visual AI and computer vision is annotation, which can be both costly and time-consuming. Today, we’re introducing Verified Auto Labeling, a new approach to AI-assisted annotation that achieves up to 95% of human-level performance while