search

CuriousAI / mean-teacher

A state-of-the-art semi-supervised method for image recognition
https://arxiv.org/abs/1703.01780
Other
1.56k stars 331 forks source link

what is ShiftConvDownsample in ResNext and shakeshake26 #18

Open liangzimei opened 5 years ago

liangzimei commented 5 years ago

hi , firstly thanks for your great work for ssl. But when i refer many resnext nets of pytorch, there are no ShiftConvDownsample layer? what is the function of it? And mean teacher didn't use this layer in the experiment of cifar10 and imagenet, right? And the two fc layers after avepooling correspond to student and teacher? thanks in advance...

tarvaina commented 5 years ago

Hi,

I reimplemented the architecture from the Shake-shake regularization paper (which was the state of the art on CIFAR-10 dataset at the time of the writing of Mean Teacher), and they had this special downsampling layer, which apparently improves the results somewhat. It's not fundamental to Mean Teacher or even the shake-shake regularization as I've understood it.

The ResNet CIFAR-10 experiments do use the layer, the ImageNet experiments do not.

Antti

liangzimei commented 5 years ago

@tarvaina thank you for the detailed explanation, i got it. :)