TE
TechEcho
Home24h TopNewestBestAskShowJobs
GitHubTwitter
Home

TechEcho

A tech news platform built with Next.js, providing global tech news and discussions.

GitHubTwitter

Home

HomeNewestBestAskShowJobs

Resources

HackerNews APIOriginal HackerNewsNext.js

© 2025 TechEcho. All rights reserved.

Visual Introduction to Self Supervised Learning

219 pointsby amitnessabout 5 years ago

3 comments

alleycat5000about 5 years ago
Some really interesting work lately on &quot;contrastive&quot; learning, where the accuracy is really getting on par with supervised learning, e.g. <a href="https:&#x2F;&#x2F;arxiv.org&#x2F;abs&#x2F;2002.05709" rel="nofollow">https:&#x2F;&#x2F;arxiv.org&#x2F;abs&#x2F;2002.05709</a>
评论 #22451432 未加载
评论 #22445715 未加载
amitnessabout 5 years ago
Followup post on SimCLR: <a href="https:&#x2F;&#x2F;amitness.com&#x2F;2020&#x2F;03&#x2F;illustrated-simclr&#x2F;" rel="nofollow">https:&#x2F;&#x2F;amitness.com&#x2F;2020&#x2F;03&#x2F;illustrated-simclr&#x2F;</a>
trash3about 5 years ago
So instead of image annotation, self-supervised learning performs image manipulation to train a model. Then what? Is this network then piped into the original task at hand which would have required human annotations or is it simply for these made up tasks?
评论 #22447121 未加载
评论 #22449384 未加载
评论 #22447883 未加载