0
A Simple Framework for Contrastive Learning of Visual Representations
Ting Chen, Simon Kornblith, Mohammad Norouzi et al., 2020. arXiv.
Introduces SimCLR, which learns image features without labels by training a network to recognize differently augmented views of the same image.
What it's used for here
The inductive-methods survey lists it, with DINO, as a source of self-supervised features for clustering glyph images.
Cited by on this site 1 record
1 methods surveys
SRCInductive methods
Cite it
Chen, T., Kornblith, S., Norouzi, M., & Hinton, G. (2020). A Simple Framework for Contrastive Learning of Visual Representations. arXiv. https://arxiv.org/abs/2002.05709
@article{chen2020simple,
author = {Chen, Ting and Kornblith, Simon and Norouzi, Mohammad and Hinton, Geoffrey},
title = {A Simple Framework for Contrastive Learning of Visual Representations},
journal = {arXiv},
year = {2020},
url = {https://arxiv.org/abs/2002.05709}
}TY - GEN TI - A Simple Framework for Contrastive Learning of Visual Representations AU - Chen, Ting AU - Kornblith, Simon AU - Norouzi, Mohammad AU - Hinton, Geoffrey PY - 2020 JO - arXiv UR - https://arxiv.org/abs/2002.05709 ER -
Chen, Ting et al.. “A Simple Framework for Contrastive Learning of Visual Representations.” arXiv (2020).