Red line - the error rate of a trained human annotator (5.1%).

Information about the ImageNet competition is here. It's one of the most reputable competitions in the field, sponsored by the Stanford University, Princeton University, Google and A9. "While our algorithm produces a superior result on this particular dataset, this does not indicate that machine vision outperforms human vision on object recognition in general."

Source of the data:

• Dean Takahashi. Google expert explains why deep-learning neural nets are hot in everything from games to recognizing cats // VentureBeat, March 18, 2015

Additional information about the data:

• John Markoff. Machine Vision Takes Big Step // The New York Times (the New York edition). page B6. 08/25/2014
• Andrej Karpathy, Fei-Fei Li. Automated Image Captioning with ConvNets and Recurrent Nets. 2014
• Jordan Novet. Microsoft researchers say their newest deep learning system beats humans — and Google // VentureBeat, February 9, 2015
• Andrej Karpathy. What I learned from competing against a ConvNet on ImageNet // github.io. Sep 2, 2014
• O. Russakovsky, J. Deng, H. Su, J. Krause, S. Satheesh, S. Ma, Z. Huang, A. Karpathy, A. Khosla, M. Bernstein, et al. Imagenet large scale visual recognition challenge. ArXiv:1409.0575, 2014.
• Kaiming He. Xiangyu Zhang. Shaoqing Ren. Jian Sun. Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classification

Data:

• 2011 - 25,7%
• 2012 - 16,4%
• 2013 - 11,7%
• 2014 - 6,7%
• 2015 - 4,8%