Data Augmentation to Address Foggy Images Quiz 2 Question 10

[manifest]

Hey everyone

In the course video, Andrew described two cases. Both are different from the one we have in a quiz.

• With audio, we can’t rely on human judgment, because humans can only detect sounds in a frequency range from about 20 Hz to 20 kHz. The human perception is totally different – humans quite good at it.
• Distribution between artificially generated car images and real cars is quite different. At the same time, a distribution of real foggy images found on the Internet should be close to a distribution of images from the front-facing camera of a car.

@mualloc

NG mentioned that there is a potential risk while artificially data synthesizing such as NN may overfit to a some specific subset of synthesized data. He exemplified that fact by giving the example of synthesized car images may seem very real to humans but not to NN.
And my question is: doesn’t correct answer of question 10 totally ignore that fact?

In the quiz, we have quite a few foggy images and their distribution should be close to a distribution of images from the front-facing camera of a car, so answer options seem fine.

@mualloc @frippe75 @rsuriano