Self-supervised Representation Learning for Cell Event Recognition through Time Arrow Prediction
This work addresses the problem of reducing annotation requirements for cell event recognition in bioimaging, though it appears incremental as it applies an existing self-supervised technique to a specific domain.
The paper tackles the challenge of analyzing cell states in live-cell microscopy data by proposing a self-supervised representation learning approach based on time arrow prediction, which achieves better performance with limited annotations compared to fully supervised methods.
The spatio-temporal nature of live-cell microscopy data poses challenges in the analysis of cell states which is fundamental in bioimaging. Deep-learning based segmentation or tracking methods rely on large amount of high quality annotations to work effectively. In this work, we explore an alternative solution: using feature maps obtained from self-supervised representation learning (SSRL) on time arrow prediction (TAP) for the downstream supervised task of cell event recognition. We demonstrate through extensive experiments and analysis that this approach can achieve better performance with limited annotation compared to models trained from end to end using fully supervised approach. Our analysis also provides insight into applications of the SSRL using TAP in live-cell microscopy.