While I'm reading the deep learning book, I came across something as "top-5 error rate". I want to know what is it really about and how it is evaluated in ILSVRC (ImageNet Large Scale Visual Recognition challenge) ?
The Top-5 error rate is the percentage of test examples for which the correct class was not in the top 5 predicted classes.
So, for example, if a test image is a picture of a
Persian cat, and the top 5 predicted classes in order are
[Pomeranian (0.4), mongoose (0.25), dingo (0.15), Persian cat (0.1), tabby cat (0.02)], then it is still treated as being 'correct' because the actual class is in the top 5 predicted classes for this test image.
Remember to keep in mind that ImageNet has 1000 classes, so a low top-5 error rate is still not extremely easy to achieve.