# On instabilities of deep learning in image reconstruction - Does AI come at a cost?

Source: [On instabilities of deep learning in image reconstruction - Does AI come at a cost?](<https://www.sota2.com/research/paper/68fa678e1e209131cea16f75>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-10-28T13:56:42.891Z

Authors: Vegard Antun, Francesco Renna, Clarice Poon, Ben Adcock, Anders C. Hansen

Published: 2019-02-14T11:14:58.000Z

## Abstract

Deep learning, due to its unprecedented success in tasks such as image classification, has emerged as a new tool in image reconstruction with potential to change the field. In this paper we demonstrate a crucial phenomenon: deep learning typically yields unstablemethods for image reconstruction. The instabilities usually occur in several forms: (1) tiny, almost undetectable perturbations, both in the image and sampling domain, may result in severe artefacts in the reconstruction, (2) a small structural change, for example a tumour, may not be captured in the reconstructed image and (3) (a counterintuitive type of instability) more samples may yield poorer performance. Our new stability test with algorithms and easy to use software detects the instability phenomena. The test is aimed at researchers to test their networks for instabilities and for government agencies, such as the Food and Drug Administration (FDA), to secure safe use of deep learning methods.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/1902.05300>)

[PDF](<https://arxiv.org/pdf/1902.05300.pdf>)