Detector Algorithms of Bounding Box and Segmentation Mask of a Mask R-CNN Model

TL;DR

This paper evaluates the detection performance differences between bounding boxes and segmentation masks in Mask R-CNN models, highlighting that bounding boxes generally outperform masks across various classes and metrics.

Contribution

It provides a comparative analysis of detection metrics for bounding boxes and segmentation masks, emphasizing the performance disparities in Mask R-CNN outputs.

Findings

Bounding boxes outperform segmentation masks in detection accuracy.

Harmonic precision and recall values are lower for segmentation masks.

Performance differences vary across object classes.

Abstract

Detection performances on bounding box and segmentation mask outputs of Mask R-CNN models are evaluated. There are significant differences in detection performances of bounding boxes and segmentation masks, where the former is constantly superior to the latter. Harmonic values of precisions and recalls of linear cracks, joints, fillings, and shadows are significantly lower in segmentation masks than bounding boxes. Other classes showed similar harmonic values. Discussions are made on different performances of detection metrics of bounding boxes and segmentation masks focusing on detection algorithms of both detectors.