Structure-measure: A New Way to Evaluate Foreground Maps

TL;DR

This paper introduces a novel structural similarity measure called Structure-measure for evaluating foreground maps in object segmentation, emphasizing structural features aligned with human visual perception.

Contribution

The paper proposes an efficient, structure-aware evaluation metric that combines region and object-level similarity, improving upon pixel-wise error-based measures.

Findings

Outperforms existing measures on benchmark datasets

Correlates well with human visual perception

Demonstrates superiority using 5 meta-measures

Abstract

Foreground map evaluation is crucial for gauging the progress of object segmentation algorithms, in particular in the filed of salient object detection where the purpose is to accurately detect and segment the most salient object in a scene. Several widely-used measures such as Area Under the Curve (AUC), Average Precision (AP) and the recently proposed Fbw have been utilized to evaluate the similarity between a non-binary saliency map (SM) and a ground-truth (GT) map. These measures are based on pixel-wise errors and often ignore the structural similarities. Behavioral vision studies, however, have shown that the human visual system is highly sensitive to structures in scenes. Here, we propose a novel, efficient, and easy to calculate measure known an structural similarity measure (Structure-measure) to evaluate non-binary foreground maps. Our new measure simultaneously evaluates region-aware and object-aware structural similarity between a SM and a GT map. We demonstrate superiority of our measure over existing ones using 5 meta-measures on 5 benchmark datasets.