Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Path-breaking Papers About Image Classification

blog.paralleldots.com

Post reply on HN
Print view View original

1–10 of 32 posts

Re: Path-breaking Papers About Image Classification

#3

Post by parths »

pulkitkumar1995 wrote: post #2

Is densenet the one which won the best oaper award in CVPR this year? And which framework would you recommend to code these in?

Yes! Facebook's Densenet won the best paper award in CVPR this year. I would recommend PyTorch framework to code these in as it extends the numpy, scipy ecosystem and is simpler to use.

Re: Path-breaking Papers About Image Classification

#5

Post by mongodude »

parths wrote: post #3
pulkitkumar1995 wrote: post #2

Is densenet the one which won the best oaper award in CVPR this year? And which framework would you recommend to code these in?

Yes! Facebook's Densenet won the best paper award in CVPR this year. I would recommend PyTorch framework to code these in as it extends the numpy, scipy ecosystem and is simpler to use.

I'll prefer utility over hype. One has to see how the community evolves around pytorch.

Re: Path-breaking Papers About Image Classification

#6

Post by kushankpoddar »

Sometimes I wonder why is the top-5 image classification task so difficult. If you are giving me 5 chances to look at an image and correctly classify it from ~1000 Imagenet classes, I can surely do better than 5-10% error rate.

Also, now that the top-5 error rate been brought down considerably, what is the next benchmark for the research community to beat? A new dataset, top-1 error rate on Imagenet?

Re: Path-breaking Papers About Image Classification

#8

Post by parths »

kushankpoddar wrote: post #6

Sometimes I wonder why is the top-5 image classification task so difficult. If you are giving me 5 chances to look at an image and correctly classify it from ~1000 Imagenet classes, I can surely do better than 5-10% error rate. Also, now that the top-5 error rate been brought down considerably, what is the next benchmark for the research community to beat? A new dataset, top-1 error rate on Imagenet?

A large majority of human errors come from fine-grained categories(such as correctly identifying two similar cat species) and class unawareness. I would recommend this article by Andrej Karpathy, where he talks about his learning from competing against GoogLeNet: http://karpathy.github.io/2014/09/02/what-i-learned-from-com...

Re: Path-breaking Papers About Image Classification

#9

Post by muktabh »

mongodude wrote: post #4

Squeeze and excitation network by momenta.ai has been a watershed moment for Chinese AI prowess and I'll watch out for such Chinese startups to dominate AI landscape for a while. What amuses me is why Google haven't participated in the last couple imagenets?

Google has its own huge internal datasets for image classification. You can check for its mention in Chollet's ExceptionNet paper. That may be the reason why they are not really interested in working on imagenet.

Re: Path-breaking Papers About Image Classification

#10

Post by tanilama »

mongodude wrote: post #4

Squeeze and excitation network by momenta.ai has been a watershed moment for Chinese AI prowess and I'll watch out for such Chinese startups to dominate AI landscape for a while. What amuses me is why Google haven't participated in the last couple imagenets?

Imagenet as a competition is losing its importance ever since 2016. No idea like ResNet that is widely effective and inspiring from that year. I feel people just over engineered their network structure to claim the state of art by marginal gain.

Google since brought up their Neural Architecture search that can automatically design network, which I think is way ahead of rest of the competitors here.

Post reply on HN