top | item 40617619

What I learned from competing against a ConvNet on ImageNet (2014)

3 points| tosh | 1 year ago |karpathy.github.io | reply

1 comment

order
[+] KqAmJQ7|1 year ago|reply
> Fine-grained recognition. We found that humans are noticeably worse at fine-grained recognition (e.g. dogs, monkeys, snakes, birds), even when they are in clear view. To understand the difficulty, consider that there are more than 120 species of dogs in the dataset. We estimate that 28 (37%) of the human errors fall into this category, while only 7 (7%) of GoogLeNet erros do.

This is an interesting observation. It also makes claims of near-human-level performance somewhat suspect.