Self-Supervised Pretraining Improves Self-Supervised Pretraining
This addresses the resource-intensive nature of self-supervised pretraining for users lacking computational resources, offering a more efficient and robust method.
The paper tackles the problem of expensive and lengthy self-supervised pretraining in computer vision by proposing Hierarchical PreTraining (HPT), which initializes pretraining with an existing model, resulting in up to 80x faster convergence and improved accuracy across 16 datasets.
While self-supervised pretraining has proven beneficial for many computer vision tasks, it requires expensive and lengthy computation, large amounts of data, and is sensitive to data augmentation. Prior work demonstrates that models pretrained on datasets dissimilar to their target data, such as chest X-ray models trained on ImageNet, underperform models trained from scratch. Users that lack the resources to pretrain must use existing models with lower performance. This paper explores Hierarchical PreTraining (HPT), which decreases convergence time and improves accuracy by initializing the pretraining process with an existing pretrained model. Through experimentation on 16 diverse vision datasets, we show HPT converges up to 80x faster, improves accuracy across tasks, and improves the robustness of the self-supervised pretraining process to changes in the image augmentation policy or amount of pretraining data. Taken together, HPT provides a simple framework for obtaining better pretrained representations with less computational resources.