shinian

I have the same confusion, and i'd really appreciate s simple example for convolution?

> Hi, > Thanks for sharing this code. However, it seems that there is no L2 loss of intermediate features in this code. This is my question about **loss source...

> Hi, > Thanks for sharing the code, but i have some questions > > In my understanding, middle_output1, middle_output2, and middle_output3 should be different from output. But in the...

MSD is a bi-KD or mutual learning framework while the 'be your own teacher' is a one-way knowledge distillation method

> Hi， > Thanks for sharing this code and it's really helpful. > > Recently I read your paper:"MSD: Multi-Self-Distillation Learning via Multi-classifiers within Deep Neural Networks".It's a very interesting...

In fact, I faced the same problem. In my opinion, the paper's some details are not clear, such as the side-branch bottleneck architectures.