Human Attention-Guided Explainable Artificial Intelligence for Computer Vision Models. (arXiv:2305.03601v1 [cs.CV])

We examined whether embedding human attention knowledge into saliency-based
explainable AI (XAI) methods for computer vision models could enhance their
plausibility and faithfulness. We first developed new gradient-based XAI
methods for object detection models to generate object-specific explanations by
extending the current methods for image classification models. Interestingly,
while these gradient-based methods worked well for explaining image
classification models, when being used for explaining object detection models,
the resulting saliency maps generally had lower faithfulness than human
attention maps when …

artificial artificial intelligence arxiv attention classification computer computer vision detection embedding explainable ai explainable artificial intelligence gradient human image intelligence knowledge vision vision models xai