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.

PIRL: Learn Image Representations Immune to Geometric Transformation

50 pointsby amitnessabout 5 years ago

3 comments

fxtentacleabout 5 years ago
Thank you @amitness for this wonderful website with graphical explanations :)<p>The PIRL technique in question here seems useless to me, because its loss deliberately trains it to behave differently from what a human would do. But that overview page <a href="https:&#x2F;&#x2F;amitness.com&#x2F;2020&#x2F;02&#x2F;illustrated-self-supervised-learning&#x2F;" rel="nofollow">https:&#x2F;&#x2F;amitness.com&#x2F;2020&#x2F;02&#x2F;illustrated-self-supervised-lea...</a> is gold.
alisterburtabout 5 years ago
This looks a lot to me like learned image descriptors from the computer vision community. Some examples are Discriminative learning of local image descriptors (<a href="http:&#x2F;&#x2F;matthewalunbrown.com&#x2F;papers&#x2F;pami2010.pdf" rel="nofollow">http:&#x2F;&#x2F;matthewalunbrown.com&#x2F;papers&#x2F;pami2010.pdf</a>) DeepDesc (<a href="https:&#x2F;&#x2F;icwww.epfl.ch&#x2F;~trulls&#x2F;pdf&#x2F;iccv-2015-deepdesc.pdf" rel="nofollow">https:&#x2F;&#x2F;icwww.epfl.ch&#x2F;~trulls&#x2F;pdf&#x2F;iccv-2015-deepdesc.pdf</a>) L2-net (<a href="http:&#x2F;&#x2F;www.nlpr.ia.ac.cn&#x2F;fanbin&#x2F;pub&#x2F;L2-Net_CVPR17.pdf" rel="nofollow">http:&#x2F;&#x2F;www.nlpr.ia.ac.cn&#x2F;fanbin&#x2F;pub&#x2F;L2-Net_CVPR17.pdf</a>)
im3w1labout 5 years ago
The issue with this is that you (most of the time) don&#x27;t want your image representations to be immune to geometric transformation.<p>A rotated p should be recognized as a d. In nature pictures you want to recognize blue at the top as sky and blue at the bottom as water.
评论 #22613260 未加载