Appendix: Improving Contrastive Learning on Imbalanced Seed Data via Open-World Sampling

This appendix contains the following details that we could not include in the main paper due to space restrictions. B) Details of the employed hyperparameters. Our codes are based on Pytorch [1], and all models are trained with NVIDIAA100 Tensor Core GPU. B.1 Pre-training We identically follow [2] for pre-training settings except the epochs number: we pre-train for 1000 epochs for all our experiments following [3] (Including the feature extractor). B.2 Fine-tuning For all fine-tuning, the optimizer is set as SGD with momentum of 0.9 and initial learning rate of 30 following [4].