Nice article. Bayesian uncertainty seems like it could pair well with pseudo-labeling additional unlabeled training data. Could use it throw out the unconfident pseudo-labels, create weights for the pseudo-labels based on confidence, or adjust how soft the pseudo-labels are based on confidence. I’ll have to do some experiments with my current dataset and see how well Bayesian pseudo-labels works.
I was reading through your code and saw that you were using
learn.predict_with_mc_dropout for the Bayesian uncertainty predictions. For example, in
pred = learn.predict_with_mc_dropout(img,n_times=n_times)
probs = [prob.view((1,1) + prob.shape) for prob in pred]
probs = torch.cat(probs)
e = entropy(probs)
however, I couldn’t find the definition for
predict_with_mc_dropout in your Colab notebook or github repository.