top | item 16211126 (no title) schrep | 8 years ago With what precision and recall? discuss order hn newest m_ke|8 years ago Not that much worse than what you see on imagenet. Most large companies have internal datasets with >100 million images.https://arxiv.org/abs/1610.02357 schrep|8 years ago That’s impressive work. Still don’t think we have reached human level for all the categories of things we see in images. But you are correct that my comment about 1k categories is not true for many production systems. load replies (3) itsa2|8 years ago In case you didn't realize, the guy you're talking to is the CTO of what some may call a "large company." load replies (3)
m_ke|8 years ago Not that much worse than what you see on imagenet. Most large companies have internal datasets with >100 million images.https://arxiv.org/abs/1610.02357 schrep|8 years ago That’s impressive work. Still don’t think we have reached human level for all the categories of things we see in images. But you are correct that my comment about 1k categories is not true for many production systems. load replies (3) itsa2|8 years ago In case you didn't realize, the guy you're talking to is the CTO of what some may call a "large company." load replies (3)
schrep|8 years ago That’s impressive work. Still don’t think we have reached human level for all the categories of things we see in images. But you are correct that my comment about 1k categories is not true for many production systems. load replies (3)
itsa2|8 years ago In case you didn't realize, the guy you're talking to is the CTO of what some may call a "large company." load replies (3)
m_ke|8 years ago
https://arxiv.org/abs/1610.02357
schrep|8 years ago
itsa2|8 years ago