Papers of the day   All papers

Multi-task Self-Supervised Visual Learning

Comments

Oriol Vinyals: Rapid unsupervised learning progress thanks to contrastive losses, approaching supervised learning! -40% Multitask SSL https://arxiv.org/abs/1708.07860 (2017) -50% CPC https://arxiv.org/abs/1807.03748 (2018) -70% AMDIM/MOCO/CPCv2/etc (2019) -76.5% SimCLR https://arxiv.org/abs/2002.05709 (2020, so far) https://t.co/z1Q1yPi9pO

5 replies, 683 likes


Aravind Srinivas: Self-supervised learning explosion 💥

1 replies, 60 likes


Pierre Richemond: It’s confirmed : the revolution will be self-supervised.

1 replies, 8 likes


小猫遊りょう(たかにゃし・りょう): Multi-task Self-Supervised Visual Learning https://arxiv.org/abs/1708.07860

1 replies, 1 likes


Vivek Natarajan: This is really exciting! Vision's BERT moment is closer than ever.

0 replies, 1 likes


Content

Found on Feb 14 2020 at https://arxiv.org/pdf/1708.07860.pdf

PDF content of a computer science paper: Multi-task Self-Supervised Visual Learning