The troublesome kernel -- On hallucinations, no free lunches and the accuracy-stability trade-off in inverse problems

1 code implementation • 5 Jan 2020 • Nina M. Gottschling, Vegard Antun, Anders C. Hansen, Ben Adcock

In inverse problems in imaging, the focus of this paper, there is increasing empirical evidence that methods may suffer from hallucinations, i. e., false, but realistic-looking artifacts; instability, i. e., sensitivity to perturbations in the data; and unpredictable generalization, i. e., excellent performance on some images, but significant deterioration on others.

Hallucination Image Classification