Solving Inverse Problems With Deep Neural Networks -- Robustness Included?

arXiv2011.04268MaRDI QIDQ6353287

Author name not available (Why is that?)

Publication date: 9 November 2020

Abstract: In the past five years, deep learning methods have become state-of-the-art in solving various inverse problems. Before such approaches can find application in safety-critical fields, a verification of their reliability appears mandatory. Recent works have pointed out instabilities of deep neural networks for several image reconstruction tasks. In analogy to adversarial attacks in classification, it was shown that slight distortions in the input domain may cause severe artifacts. The present article sheds new light on this concern, by conducting an extensive study of the robustness of deep-learning-based algorithms for solving underdetermined inverse problems. This covers compressed sensing with Gaussian measurements as well as image recovery from Fourier and Radon measurements, including a real-world scenario for magnetic resonance imaging (using the NYU-fastMRI dataset). Our main focus is on computing adversarial perturbations of the measurements that maximize the reconstruction error. A distinctive feature of our approach is the quantitative and qualitative comparison with total-variation minimization, which serves as a provably robust reference method. In contrast to previous findings, our results reveal that standard end-to-end network architectures are not only resilient against statistical noise, but also against adversarial perturbations. All considered networks are trained by common deep learning techniques, without sophisticated defense strategies.

Has companion code repository: https://github.com/jmaces/robust-nets

This page was built for publication: Solving Inverse Problems With Deep Neural Networks -- Robustness Included?

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6353287)