Open ogencoglu opened 11 months ago
Thanks for your comment and interest in our work!
It has been a busy few weeks on our end, but a better packaging for our method is in our radar - we are hoping to do that in the near future.
We have focused on image classification so far; although we have not tested it in other vision tasks, I believe there is a good chance they will be helpful. Other modalities is definitely a good venue to explore - but something we have not done yet.
Thanks for the interesting work!
It would be quite beneficial if these methods can be provided as a ready to use class that follows albumentation API which is probably the most used augmentation library. A
pip
package would also increase the adoption.Is there anything in your method that is specific to image clasification? Can it be utilized in semantic or instance segmentation or even in other modalities such as audio/speech?