Human Attention-Guided Explainable Artificial Intelligence for Computer Vision Models
This work addresses the need for more interpretable AI in computer vision, particularly for object detection, though it is incremental as it builds on existing gradient-based XAI methods.
The authors tackled the problem of improving explainable AI (XAI) for computer vision models by embedding human attention knowledge, resulting in HAG-XAI, which enhanced plausibility and faithfulness for object detection models and outperformed existing methods.
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 performing the same task. We then developed Human Attention-Guided XAI (HAG-XAI) to learn from human attention how to best combine explanatory information from the models to enhance explanation plausibility by using trainable activation functions and smoothing kernels to maximize XAI saliency map's similarity to human attention maps. While for image classification models, HAG-XAI enhanced explanation plausibility at the expense of faithfulness, for object detection models it enhanced plausibility and faithfulness simultaneously and outperformed existing methods. The learned functions were model-specific, well generalizable to other databases.