no code implementations • 28 Oct 2021 • Aurelia Bustos, Artemio Payá, Andres Torrubia, Rodrigo Jover, Xavier Llor, Xavier Bessa, Antoni Castells, Cristina Alenda
A systematic study of biases at tile level identified three protected (bias) variables associated with the learned representations of a baseline model: the project of origin of samples, the patient spot and the TMA glass where each spot was placed.