Pseudosaccades: A simple ensemble scheme for improving classification performance of deep nets

Jin Sean Lim, Robert John Durrant

Abstract:

We describe a simple ensemble approach that, unlike conventional ensembles,
uses multiple random data sketches (‘pseudosaccades’) rather than multiple classifiers
to improve classification performance. Using this simple, but novel, approach
we obtain statistically significant improvements in classification performance on
AlexNet, GoogLeNet, ResNet-50 and ResNet-152 baselines on Imagenet data –
e.g. of the order of 0.3% to 0.6% in Top-1 accuracy and similar improvements in
Top-k accuracy – essentially nearly for free.

Keywords: Ensemble classification, random subspace, data sketching

TL;DR: Inspired by saccades we describe a simple, cheap, effective way to improve deep net performance on an image labelling task.