Structure-Measure: A New Way to Evaluate Foreground Maps

• Published in: International journal of computer vision Vol. 129; no. 9; pp. 2622 - 2638
• Main Authors: Cheng, Ming-Ming, Fan, Deng-Ping
• Format: Journal Article
• Language: English
• Published: New York Springer US 01.09.2021; Springer; Springer Nature B.V
• Subjects: Algorithms; Analysis; Artificial Intelligence; Computer Imaging; Computer Science; Evaluation; Gaging; Image Processing and Computer Vision; Image segmentation; Object recognition; Pattern Recognition; Pattern Recognition and Graphics; Salience; Similarity; Vision; Evaluation; Foreground maps; Structure measure; Salient object detection; S-measure
• ISSN: 0920-5691; 1573-1405
• DOI: 10.1007/s11263-021-01490-8

Foreground map evaluation is crucial for gauging the progress of object segmentation algorithms, in particular in the field of salient object detection where the purpose is to accurately detect and segment the most salient object in a scene. Several measures (e.g., area-under-the-curve, F1-measure, average precision, etc.) have been used to evaluate the similarity between a foreground map and a ground-truth map. The existing 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 (0.005 s per image), and easy to calculate measure known as S-measure (structural measure) to evaluate foreground maps. Our new measure simultaneously evaluates region-aware and object-aware structural similarity between a foreground map and a ground-truth map. We demonstrate superiority of our measure over existing ones using 4 meta-measures on 5 widely-used benchmark datasets. Furthermore, we conduct a behavioral judgment study over a new database. Data from 45 subjects shows that on average they preferred the saliency maps chosen by our measure over the saliency maps chosen by the state-of-the-art measures. Our experimental results offer new insights into foreground map evaluation where current measures fail to truly examine the strengths and weaknesses of models. Code: https://github.com/DengPingFan/S-measure .