Scaling and Benchmarking Self-Supervised Visual Representation Learning

3 May 2019Priya GoyalDhruv MahajanAbhinav GuptaIshan Misra

Self-supervised learning aims to learn representations from the data itself without explicit manual supervision. Existing efforts ignore a crucial aspect of self-supervised learning - the ability to scale to large amount of data because self-supervision requires no manual labels... (read more)

PDF Abstract

Evaluation results from the paper


  Submit results from this paper to get state-of-the-art GitHub badges and help community compare results to other papers.