e92381dba235a8309f08ce46376189a9-Supplemental-Conference.pdf

We use the symmetrized cosine similarity loss from SimSiam. Model details For CIFAR10, we use pretrained StyleGAN available at the official website of StyleGAN-Ada[31]2. We also experimented with the model with best Inception score3 but did not observe significant difference in results. Linear classification The quality of the pretrained representations is evaluated by training a supervised linear classifier on frozen representationshinthe training set, and then testing itinthe validationset.