Deep_Metric
Deep_Metric copied to clipboard
Distance weighted margin loss
Hi, I wonder if you also tried the distance weighted margin loss specified in Sampling Matters in Deep Embedding Learning.
I see you have the sampling scheme applied to deviance loss. I wonder why?
Sorry for late response. I have tried to do this. But now I only have implemented the distance weighted sampling for negative pairs in a different way compared with the article . I have not implemented the Dynamic margin.