Variance Aware Training for Deep Neural Networks

Home

Discover

Bookmarks

Keep Up With Top Trending Papers In CS / AI / ML ...

Source arXiv

Computer Vision

Variance Aware Training for Deep Neural Networks

About Explicit Variance Minimization: Training Neural Networks for Medical Imaging With Limited Data Annotations

We propose the variance-aware training (vat) method that exploits this property by introducing the variance error into the model loss function, i.e., enabling minimizing the variance explicitly.

Our method requires selecting only one hyper-parameter and was able to match or improve the state-of-the-art performance of self-supervised methods while achieving an order of magnitude reduction in the model training time.

We validated the proposed method on three medical imaging datasets from diverse domains and various learningobjectives.