MoCo v-3

'MoCo v3' is a benchmark dataset used to evaluate the performance of self-supervised learning methods for Vision Transformers (ViT).

Papers using MoCo v-3 (2)

An Empirical Study Of Training Self-supervised Vision Transformers2021 · 1,448 citesImproving Visual Prompt Tuning For Self-supervised Vision Transformers2023 · 7 cites