Geometric Contrastive Learning
Published in Proceedings of the 4th Visual Inductive Priors for Data-Efficient Deep Learning Workshop at ICCV, 2023
Contrastive learning has been a long-standing research area due to its versatility and importance in learning representations. Recent works have shown improved results if the learned representations are constrained to be on a hy- persphere. However, this prior geometric constraint is not fully utilized during training. In this work, we propose mak- ing use of geodesic distances on the hypersphere to learn contrasts between representations. (oral)
Yeskendir Koishekenov, Sharvaree Vadgama*, Riccardo Valperga*, Erik J. Bekkers