André Araujo

Thanks! On Thursday, July 28, 2016, Sergey Zagoruyko [email protected] wrote: > @andrefaraujo https://github.com/andrefaraujo no, not used anywhere > > — > You are receiving this because you were mentioned. >...

Thanks! No problem if you don't have the curve, I am definitely more interested in the final value. I am training a ResNet50 with ArcFace loss, GeM pooling, whitening layer,...

Thanks for all of these answers! I understand much better now, but am still confused about a few things: - 2 Let me check if my understanding is correct: There...

Thanks @geyuying for all answers to my questions! I understand everything much better now :)

Thanks a lot for your quick response, @feymanpriv! Looking forward to having all the results with the query being cropped. Please feel free to reply to this github issue once...

Hi @feymanpriv , just a friendly ping here. Were you able to obtain the results with the fixed cropping? Thanks again!

Thanks @sungonce for the experiments and for looping me in here! Indeed as expected the numbers go down in the 1M evals. The numbers still look quite high to me,...

To explain my reasoning on why I wouldn't have expected such high DOLG performance in the 1M evals: if we look at Tab 1 in the DOLG paper, we see...

Thanks again @sungonce ! > Presumably, the authors' reproducing method also contributed to the performance difference between the DELGs to some extent. I see, that would indeed make sense. >...

Thanks @feymanpriv for the update. Looking forward to the 1M results soon!