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.

Paper claims perfect accuracy on image recognition datasets

2 pointsby bicsiabout 3 years ago

4 comments

version_fiveabout 3 years ago
At face value I&#x27;m suspicious, I thought that there were genuine ambiguities or label errors in some of those datasets that makes it very surprising you could even really define 100% accuracy.<p>Also, reading the paper a bit, it&#x27;s either badly written and I just don&#x27;t understand what they&#x27;re saying at all, or BS. It doesn&#x27;t really explain anything about their implementation, it just says they did do and got 100% accuracy, and throws in a bunch of jargon. Maybe I&#x27;m just not familiar with this area enough, but the way it&#x27;s laid out raises even more red flags
bicsiabout 3 years ago
Also, can anybody share a more informal high-level intuition about what this ‘Learning with signatures’ approach is about? It seems to be a rather recent topic in Learning (paper cites 2019+ publications)
hprotagonistabout 3 years ago
ok but AFHQ dataset, Four Shapes, MNIST and CIFAR10 are baby datasets; do this on COCO or pascal VOC or imagenet...
Mengel67about 3 years ago
Awesome and interesting article. Great things you’ve always shared with us. Thanks. Just continue composing this kind of post. <a href="https:&#x2F;&#x2F;www.myaccountaccess.one&#x2F;" rel="nofollow">https:&#x2F;&#x2F;www.myaccountaccess.one&#x2F;</a>