2

Focal Sampling SGD Biased towards Early Important Samples for Efficient Image Classification with Augmentation Selection
We propose Focal Sampling, a method that biases SGD towards samples that are found to be more important after a few training epochs, by sampling them more often for the rest of the training.
Alessio Quercia, Fernanda Nader, Abigail Morrison, Hanno Scharr, Ira Assent
PDF Cite Code
Focal Sampling SGD Biased towards Early Important Samples for Efficient Image Classification with Augmentation Selection