What do different evaluation metrics tell us about saliency models?
This work addresses the open problem of evaluating saliency models for predicting human gaze, offering transparency and guidance for researchers in computer vision.
The paper analyzes 8 evaluation metrics for saliency models to understand how they rank models based on properties like false positives and spatial deviations, providing interpretability and recommendations for metric selection under specific assumptions.
How best to evaluate a saliency model's ability to predict where humans look in images is an open research question. The choice of evaluation metric depends on how saliency is defined and how the ground truth is represented. Metrics differ in how they rank saliency models, and this results from how false positives and false negatives are treated, whether viewing biases are accounted for, whether spatial deviations are factored in, and how the saliency maps are pre-processed. In this paper, we provide an analysis of 8 different evaluation metrics and their properties. With the help of systematic experiments and visualizations of metric computations, we add interpretability to saliency scores and more transparency to the evaluation of saliency models. Building off the differences in metric properties and behaviors, we make recommendations for metric selections under specific assumptions and for specific applications.