we propose a more general framework that can also be adopted to orient whole objects and perform rotation-invariant

Moreover, as recently shown in Bai et al . in "D3Feat: Joint Learning of Dense Detection We will add this information to the revised version. As suggested, we will use only the term orientation . We will modify it in the final version of the paper. We agree that the domain of Spherical CNNs feature maps is key and we will better highlight it in the final version. Since we seek for one rotation, the loss function in (6) is applied once, and only to the last layer of the network.