Logo Logo
Help
Contact
Switch Language to German

Paschali, Magdalini; Simson, Walter; Roy, Abhijit Guha; Goebl, Rüdiger; Wachinger, Christian and Navab, Nassir (2019): Manifold Exploring Data Augmentation with Geometric Transformations for Increased Performance and Robustness. In: Information Processing in Medical Imaging, Ipmi 2019, Vol. 11492: pp. 517-529

Full text not available from 'Open Access LMU'.

Abstract

In this paper we propose a novel augmentation technique that improves not only the performance of deep neural networks on clean test data, but also significantly increases their robustness to random transformations, both affine and projective. Inspired by ManiFool, the augmentation is performed by a line-search manifold-exploration method that learns affine geometric transformations that lead to the misclassification on an image, while ensuring that it remains on the same manifold as the training data. This augmentation method populates any training dataset with images that lie on the border of the manifolds between two-classes and maximizes the variance the network is exposed to during training. Our method was thoroughly evaluated on the challenging tasks of fine-grained skin lesion classification from limited data, and breast tumor classification of mammograms. Compared with traditional augmentation methods, and with images synthesized by Generative Adversarial Networks our method not only achieves state-of-the-art performance but also significantly improves the network's robustness.

Actions (login required)

View Item View Item