The parameters of the experiment of the cowMix mask

Question

The parameters of the experiment of the cowMix mask

Closed this issue 3 years ago · 2 comments

Answer 1 · 2021-06-05T06:45:23.000Z

In the /utils/transformmasks.py, how are the parameters of sigma, p set in the functions generate_cow_mask?

Answer 2 · 2021-06-20T20:42:43.000Z

Hi, sorry for late response. The parameters used are the same as the ones used in the paper ClassMix: Segmentation-Based Data Augmentation for Semi-Supervised Learning, namely p = 0.5 and sigma taken randomly in the range [8,32]. See this repo for details on the generation and implementation.
The reason for using these particular values is partly because they were used in this existing work, and partly because they worked well empirically.