SortedAP: Rethinking evaluation metrics for instance segmentation

TL;DR

This paper introduces SortedAP, a new evaluation metric for instance segmentation that provides a more continuous and comprehensive assessment of segmentation quality, addressing limitations of existing metrics.

Contribution

The paper proposes SortedAP, a novel metric that offers a more sensitive and uninterrupted evaluation of instance segmentation performance compared to traditional metrics.

Findings

SortedAP decreases strictly with segmentation imperfections

Provides a continuous penalization scale

Outperforms existing metrics in sensitivity and resolution

Abstract

Designing metrics for evaluating instance segmentation revolves around comprehensively considering object detection and segmentation accuracy. However, other important properties, such as sensitivity, continuity, and equality, are overlooked in the current study. In this paper, we reveal that most existing metrics have a limited resolution of segmentation quality. They are only conditionally sensitive to the change of masks or false predictions. For certain metrics, the score can change drastically in a narrow range which could provide a misleading indication of the quality gap between results. Therefore, we propose a new metric called sortedAP, which strictly decreases with both object- and pixel-level imperfections and has an uninterrupted penalization scale over the entire domain. We provide the evaluation toolkit and experiment code at https://www.github.com/looooongChen/sortedAP.