Questions on masked area
jwfanDL opened this issue · 0 comments
jwfanDL commented
Hi Zhendong,
In ViTKD, we only distill the knowledge from unmasked area, while full area in MGD.
My questions are:
- Why ViTKD only distill the knowledge only from unmasked area
- What is the difference and relationship between unmasked and masked area in distillation.