Chenyang Si

Mugs: A Multi-Granular Self-Supervised Learning Framework

2022 · arXiv (Cornell University)

In self-supervised learning, multi-granular features are heavily desired though rarely investigated, as different downstream tasks (e.g., general and fine-grained classification) often require different or multi-granular features, e.g.~fine- or coarse-grained one or their mixture. In this …