Student Collaboration Improves Self-Supervised Learning: Dual-Loss Adaptive Masked Autoencoder for Brain Cell Image Analysis. (arXiv:2205.05194v1 [cs.CV])

Self-supervised learning leverages the underlying data structure as the
source of the supervisory signal without the need for human annotation effort.
This approach offers a practical solution to learning with a large amount of
biomedical data and limited annotation. Unlike other studies exploiting data
via multi-view (e.g., augmented images), this study presents a self-supervised
Dual-Loss Adaptive Masked Autoencoder (DAMA) algorithm established from the
viewpoint of the information theory. Specifically, our objective function
maximizes the mutual information by minimizing the conditional …

analysis arxiv autoencoder brain collaboration cv image learning loss masked autoencoder self-supervised learning supervised learning