Masking your problems away
Showing the effect of adding a masking layer on out of distribution accuracy
Q.A. Nouwens (TU Delft - Electrical Engineering, Mathematics and Computer Science)
J.W. Böhmer – Mentor (TU Delft - Electrical Engineering, Mathematics and Computer Science)
D.M.J. Tax – Mentor (TU Delft - Electrical Engineering, Mathematics and Computer Science)
More Info
expand_more
Other than for strictly personal use, it is not permitted to download, forward or distribute the text or part of it, without the consent of the author(s) and/or copyright holder(s), unless the work is under an open content license such as Creative Commons.
Abstract
Spurious correlation can be detrimental to performance of machine learning solutions on data that it has never seen before. This could be disastrous in situations where the prediction is important and the situation is ever changing. This paper investigates whether adding a masking layer can improve the accuracy of machine learning models on visual data, where the background is different during training and testing. A new dataset is created that overlays MNIST numbers on CIFAR-10 images, where during training only a distinct subset of background images for every label is presented to the model. The performance is measured by supplying the model with an unseen foreground sample on a background that was not encountered during training. This paper then shows that adding a masking layer can improve the performance of a model. This improvement depends on the implementation and the dataset on which the model is trained and tested.