Computer Vision News - March 2022

37 Mara Graziani from multiple institutions is handled by an additional adversarial branch that removes the domain information from the internal features. This architecture outperforms conventional CNN-based approaches for the prediction of tumor vs. normal regions in histology slides . Acknowledgement This research was supported by the EU Horizon 2020 projects PROCESS, AI4Media and ExaMode. learning texture differences rather than shapes and scale. These biases may affect thegeneralization if newscanningprotocols orequipment areadoptedby the laboratory. To counter this limitation, we developed a multi-task adversarial architecture that encourages the learningof clinical features . Thismodel has anadditional branch for each clinical feature that is important to predict tumorous regions, e.g. nuclei density, size and appearance. The shift across data