AI RESEARCH
Self-Supervised Representation Learning via Hyperspherical Density Shaping
arXiv CS.CV
•
ArXi:2604.24498v1 Announce Type: new Modern self-supervised representation learning methods often relies on empirical heuristics that are not theoretically grounded. In this study we propose HyDeS, a theoretically grounded method based on multi-view mutual information maximization within an hyperspherical space using Shannon differential entropy with a non-parametric von Mises-Fisher density estimator.