Self-Supervised Detection of Perfect and Partial Input-Dependent Symmetries

arXiv:2312.12223v3 Announce Type: replace-cross
Abstract: Group equivariance can overly constrain models if the symmetries in the group differ from those observed in data. While common methods address this by determining the appropriate level of symmetry at the dataset level, they are limited to supervised settings and ignore scenarios in which multiple levels of symmetry co-exist in the same dataset. In this paper, we propose a method able to detect the level of symmetry of each input without the need for …

arxiv cs.cv cs.lg detection input replace type