Closed nottombrown closed 5 years ago
I think that this would be most relevant for the bird-or-bicycle
dataset (because that's what the original authors designed it for), and need not be added to MNIST.
@hendrycks has volunteered to be the author of this after the ICLR crunch https://github.com/hendrycks/robustness/issues/2#issuecomment-423273663 Thanks!
Added in #51
I think that the transformations from Benchmarking Neural Network Robustness to Common Corruptions and Surface Variations by Dan Hendrycks and Tom Dietterich would be a good addition to the warmup attacks.
Three reasons why I think that this would be a good addition:
Tasks
bird-or-bicycle
dataset (Perhaps 10 transformations per image)