Data Efficient Contrastive Learning in Histopatholgy using Active Sampling
share
Deep Learning based diagnostics systems can provide accurate and robust quantitative analysis in digital pathology. Training these algorithms requires large amounts of annotated data which is impractical in pathology due to the high resolution of histopathological images. Hence, self-supervised methods have been proposed to learn features using ad-hoc pretext tasks. The self-supervised training process is time consuming and often leads to subpar feature representation due to a lack of constrain on the learnt feature space, particularly prominent under data imbalance. In this work, we propose to actively sample the training set using a handful of labels and a small proxy network, decreasing sample requirement by 93
READ FULL TEXT