Position: Do Not Explain Vision Models Without Context
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’s obvious, why don’t 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) show examples of failures of popular XAI methods, (3) provide examples of real-world use cases where spatial context plays a significant role, (4) propose new research directions that may lead to better use of context information in explaining computer vision models, (5) argue that a change in approach to explanations is needed from where to how.
Cite
Text
Tomaszewska and Biecek. "Position: Do Not Explain Vision Models Without Context." International Conference on Machine Learning, 2024.Markdown
[Tomaszewska and Biecek. "Position: Do Not Explain Vision Models Without Context." International Conference on Machine Learning, 2024.](https://mlanthology.org/icml/2024/tomaszewska2024icml-position/)BibTeX
@inproceedings{tomaszewska2024icml-position,
title = {{Position: Do Not Explain Vision Models Without Context}},
author = {Tomaszewska, Paulina and Biecek, Przemyslaw},
booktitle = {International Conference on Machine Learning},
year = {2024},
pages = {48390-48403},
volume = {235},
url = {https://mlanthology.org/icml/2024/tomaszewska2024icml-position/}
}