Learning Efficient Coding of Natural Images with Maximum Manifold Capacity Representations

1 code implementation • NeurIPS 2023 • Thomas Yerxa, Yilun Kuang, Eero Simoncelli, SueYeon Chung

The resulting method is closely related to and inspired by advances in the field of self supervised learning (SSL), and we demonstrate that MMCRs are competitive with state of the art results on standard SSL benchmarks.

Contrastive Learning Object Recognition +1