Open suyeecav opened 5 years ago
Hi!
We didn't tune hyperparameters too much for Inceptionv3/ResNet/VGG (in fact I think we used the same hyperparameters for all three) but we've never tried DenseNet---in general, we would suggest doing a hyperparameter grid with, e.g. 100 images (should be pretty fast) and then using the best hyperparameters from there.
How sensitive are the hyperparameters to different ImageNet models? I currently tested targeted attacks (slight modifications to attack loss and instance update rule) on densenet model, but the failure rate is pretty high (~50%). After careful sanity check, it seems hyperparameters might be be the main reason, especially for targeted attacks. Any guidance on this will be helpful, thanks!