ImageWang & Self-Supervised Learning

Hey everyone, so I was looking at the ImageNette, ImageWoof repo and came across an ImageWang dataset for self-supervised learning. There’s also some implementations for fastai v2:

It looks similar to SimCLR?

Has anyone done any work on using unlabeled images to pretrain the backbone? The one thing I’m stuck on is how/why is the output set to 128 in that notebook. I thought the contrastive loss thing is like a softmax, but it “softmax-es” various patches of images as to how similar they are to each other. So shouldn’t the output be 2?

Maybe this would be of interest to you:

1 Like

Thanks, but this tutorial is for rotation. I’m referring to the contrastive loss method. In that method they have 8 rotations, so 8 outputs make sense. I still don’t get where the 128 outputs is coming from in the SimCLR fastai repo…