Antonin Vobecky presents Contrastive learning for visual representations - Part 2
On 2020-12-10 11:00:00 at https://meet.google.com/wax-usyc-zow
Online reading group on "Contrastive learning for visual representations" -
Part 2
Contrastive learning has recently attracted a lot of attention as a means to
learn visual representation in an unsupervised way. This is the second part,
out of two, presenting some of the relevant approaches. We will present [1]
which
introduces a simpler approach for contrastive unsupervised learning, and
continue the discussion with [2] which discusses the benefits of models trained
without
supervision even in setups of additional training with labeling.
[1] A Simple Framework for Contrastive Learning of Visual Representations
, Chen et al., arxiv 2020 https://arxiv.org/abs/2002.05709
[2] Big Self-Supervised Models are Strong Semi-Supervised Learners, Chen et
al.,
arxiv 2020 https://arxiv.org/abs/2006.10029
Video conference link: https://meet.google.com/wax-usyc-zow
Instructions: http://cmp.felk.cvut.cz/~toliageo/rg/instructions.html
Instructions for participants: The reading group studies the literature in the
field of pattern recognition and computer vision. At each meeting one or more
papers are prepared for presentation by a single person, the presenter. The
meetings are open to anyone, disregarding their background. It is assumed that
everyone attending the reading group has, at least briefly, read the paper –
not necessarily understanding everything. Attendants should preferably send
questions about the unclear parts to the speaker at least one day in advance.
During the presentation we aim to have a fruitful discussion, a critical
analysis of the paper, as well as brainstorming for creative extensions.
See the page of reading groups
http://cmp.felk.cvut.cz/~toliageo/rg/index.html
Part 2
Contrastive learning has recently attracted a lot of attention as a means to
learn visual representation in an unsupervised way. This is the second part,
out of two, presenting some of the relevant approaches. We will present [1]
which
introduces a simpler approach for contrastive unsupervised learning, and
continue the discussion with [2] which discusses the benefits of models trained
without
supervision even in setups of additional training with labeling.
[1] A Simple Framework for Contrastive Learning of Visual Representations
, Chen et al., arxiv 2020 https://arxiv.org/abs/2002.05709
[2] Big Self-Supervised Models are Strong Semi-Supervised Learners, Chen et
al.,
arxiv 2020 https://arxiv.org/abs/2006.10029
Video conference link: https://meet.google.com/wax-usyc-zow
Instructions: http://cmp.felk.cvut.cz/~toliageo/rg/instructions.html
Instructions for participants: The reading group studies the literature in the
field of pattern recognition and computer vision. At each meeting one or more
papers are prepared for presentation by a single person, the presenter. The
meetings are open to anyone, disregarding their background. It is assumed that
everyone attending the reading group has, at least briefly, read the paper –
not necessarily understanding everything. Attendants should preferably send
questions about the unclear parts to the speaker at least one day in advance.
During the presentation we aim to have a fruitful discussion, a critical
analysis of the paper, as well as brainstorming for creative extensions.
See the page of reading groups
http://cmp.felk.cvut.cz/~toliageo/rg/index.html