Let's say I have a bunch of images from ImageNet and their corresponding labels, I also have a set of labels that aren't labeled and I'd like to label them, what are some semi-supervised methods/techniques in general that I can use to label them?

One obvious answer is to train a classifier/use ViT or something similar to get the labels, but I'm looking for semi-supervised learning techniques here.



Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy