decoupledlearning
3953630da28e5181cffca1278517e3cf-Supplemental.pdf
However, ifτ is too high, most of the unlabeled data points would not be used for consistency regularization. Based on these insights, we setτ as 0.95 in our experiments. We describe further details of the experimental setup. To train the ReMixMatch, we gradually increased the coefficient of the loss associated with the unlabeled data points, following [4]. We found that without this gradual increase, the validation loss of the ReMixMatch did not converge.
Technology: Information Technology > Artificial Intelligence > Machine Learning > Unsupervised or Indirectly Supervised Learning (0.56)