1 code implementation • 28 Sep 2020 • Souradip Chakraborty, Aritra Roy Gosthipaty, Sayak Paul
In this work, we propose that, with the normalized temperature-scaled cross-entropy (NT-Xent) loss function (as used in SimCLR), it is beneficial to not have images of the same category in the same batch.
1 code implementation • 25 Sep 2020 • Souradip Chakraborty, Aritra Roy Gosthipaty, Sayak Paul
In this work, we propose that, with the normalized temperature-scaled cross-entropy (NT-Xent) loss function (as used in SimCLR), it is beneficial to not have images of the same category in the same batch.