using log_coral_loss with large activation about minimal-entropy-correlation-alignment HOT 3 CLOSED

Thank you for your kind reply!

I would try the simple one(averaging across spatial dimension) first!

Best,
Yoo

from minimal-entropy-correlation-alignment.

Hi,
thanks for you comment!
So, I understand you want to compute covariance in between a batch of images (or feature maps).
Easiest thing you could try is to average across spatial dimensions, in order to get an average feature vector [200,176] for your image/feature map. Alternatively, a flatten+FC layer could help you reducing the dimension in order to get a vector.
Both of the alternatives, however, are somehow 'destroying' spatial correlation. You should probably ask yourself what kind of correlation is important in your problem.
Hope this discussion could be of any help in your research.
Best,
P.

from minimal-entropy-correlation-alignment.

Wish you good luck with you project!

from minimal-entropy-correlation-alignment.