Hard Example Mining

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

Focal Sampling SGD Biased towards Early Important Samples for Efficient Image Classification with Augmentation Selection

SGD Biased towards Early Important Samples for Efficient Training

Biasing SGD towards samples found to be more important early in training to improve training efficiency.

Alessio Quercia, Abigail Morrison, Hanno Scharr, Ira Assent

SGD Biased towards Early Important Samples for Efficient Training