1 code implementation • ICLR 2021 • Joseph D. Viviano, Becks Simpson, Francis Dutil, Yoshua Bengio, Joseph Paul Cohen
In some prediction tasks, such as for medical images, one may have some images with masks drawn by a human expert, indicating a region of the image containing relevant information to make the prediction.
no code implementations • 25 Sep 2019 • Joseph D Viviano, Becks Simpson, Francis Dutil, Yoshua Bengio, Joseph Paul Cohen
We describe a simple method for taking advantage of such auxiliary labels, by training networks to ignore the distracting features which may be extracted outside of the region of interest, on the training images for which such masks are available.
1 code implementation • 19 Aug 2019 • Kyle Young, Gareth Booth, Becks Simpson, Reuben Dutton, Sally Shrapnel
We show that despite high accuracy, the models will occasionally assign importance to features that are not relevant to the diagnostic task.
no code implementations • 16 Apr 2019 • Becks Simpson, Francis Dutil, Yoshua Bengio, Joseph Paul Cohen
With too few samples or too many model parameters, overfitting can inhibit the ability to generalise predictions to new data.