Supervised Contrastive Learning-Supplementary Material

In Fig. 1, we compare the training setup for the cross-entropy, self-supervised contrastive and supervised contrastive (SupCon) losses. Note that the number of parameters in the inference models always stays the same. We also note that it is not necessary to train a linear classifier in the second stage, and previous works have used k-Nearest Neighbor classification [12] or prototype classification to evaluate representations on classification tasks. The linear classifier can also be trained jointly with the encoder, as long as it doesn’t propagate gradients back to the encoder.