Profile cover photo
Profile photo
Abhinav Gupta
346 followers
346 followers
About
Posts

Post has shared content
Our work on training ConvNets with 300M images!
As researchers, we have always wondered: if we scale up the amount of training data for computer vision deep learning models by 10x, will the accuracy double? How about 100x or maybe even 300x? Will the accuracy plateau or will we continue to see increasing gains with more and more data? We explore this on the Research blog as we Revisit the Unreasonable Effectiveness of Data.
Add a comment...

Post has attachment

Post has attachment

Post has shared content

Post has attachment
Add a comment...

Post has attachment

having success in getting reviews improved :)
Add a comment...

Post has attachment
Add a comment...

Post has attachment

Post has shared content
Our new SIGGRAPH ASIA paper
The power of single-instance "exemplar-based" SVMs for image matching cannot be over-exaggerated.
Add a comment...
Wait while more posts are being loaded