All the results are lower than paper with the default settings and feature pyramid 5,2,1

[Germany321]

I have tried FCN pyramid structure 5,2,1 in the paper, but the accuracy on miniImagenenet is still 65.5%. Besides, acc on tiered imagenet is 70.6%(2% lower), 72.8%(2% lower) on CIFAR-FS, 45.7% on FC100(1% lower) and 76.6%(0.5% lower). I used raw code and keep the pyramid FCN as 5,2,1, all the results are lower than paper.

[Germany321]

I mean the results on the arxiv paper. Are the results on the table 7 trained with the auxiliary loss?