Position paper: Do not explain (vision models) without context

arXiv:2404.18316v1 Announce Type: cross
Abstract: Does the stethoscope in the picture make the adjacent person a doctor or a patient? This, of course, depends on the contextual relationship of the two objects. If it is obvious, why don not explanation methods for vision models use contextual information? In this paper, we (1) review the most popular methods of explaining computer vision models by pointing out that they do not take into account context information, (2) provide examples of real-world use …

abstract arxiv context course cs.cv cs.lg doctor information objects of course paper patient person relationship type vision vision models