On the Capability of CNNs to Generalize to Unseen Category-Viewpoint Combinations

no code implementations • 1 Jan 2021 • Spandan Madan, Timothy Henry, Jamell Arthur Dozier, Helen Ho, Nishchal Bhandari, Tomotake Sasaki, Fredo Durand, Hanspeter Pfister, Xavier Boix

We find that learning category and viewpoint in separate networks compared to a shared one leads to an increase in selectivity and invariance, as separate networks are not forced to preserve information about both category and viewpoint.

Object Recognition Viewpoint Estimation