You are all cordially invited to the AMLab seminar on Tuesday May 30 at 16:00 in C3.163 (FNWI, Amsterdam Science Park), where Maurice Weiler will give a talk titled “Learning steerable filters for rotation-equivariant CNNs”. Afterwards there are the usual drinks and snacks.
Abstract: Besides translational invariances, a broad class of images like medical or astronomical data exhibits rotational invariances. While such a priori knowledge was typically exploited by data augmentation, recent research shifts focus to directly implementing rotational equivariance into model architectures. I will present Steerable Filter CNNs which efficiently incorporate rotation equivariance by learning steerable filters. Two approaches, based on orientation-pooling or group-convolutions, are presented and discussed. A common weight initialization scheme is generalized to networks which learn filter banks as a linear combination of a fixed system of atomic filters.