Facebook Used Billions Of Instagram Photos To Set A New Record In Image Recognition Accuracy
02/05/2018
The work, known as weakly supervised pre-training, got an accuracy score of 85.4% when applied to a common benchmarking tool–fully 2% better than the previous state of the art.
Facebook is leveraging billions of Instagram photos and thousands of user-added hashtags to improve the state of the art of image...
The work, known as weakly supervised pre-training, got an accuracy score of 85.4% when applied to a common benchmarking tool–fully 2% better than the previous of the art.
Facebook is leveraging of Instagram and thousands of user-added hashtags to improve the of the art of image recognition.Read Full Story