Context-measure: Contextualizing Metric for Camouflage

TL;DR

This paper introduces Context-measure, a new evaluation metric for camouflaged object segmentation that incorporates spatial context and pixel-wise correlation, aligning better with human perception.

Contribution

The paper proposes a novel probabilistic pixel-aware correlation framework for context-dependent evaluation of camouflaged objects, improving reliability over existing metrics.

Findings

Context-measure outperforms existing metrics in reliability.

It aligns better with human perception.

Applicable across diverse camouflaged scenarios.

Abstract

Camouflage is primarily context-dependent yet current metrics for camouflaged scenarios overlook this critical factor. Instead, these metrics are originally designed for evaluating general or salient objects, with an inherent assumption of uncorrelated spatial context. In this paper, we propose a new contextualized evaluation paradigm, Context-measure, built upon a probabilistic pixel-aware correlation framework. By incorporating spatial dependencies and pixel-wise camouflage quantification, our measure better aligns with human perception. Extensive experiments across three challenging camouflaged object segmentation datasets show that Context-measure delivers more reliability than existing context-independent metrics. Our measure can provide a foundational evaluation benchmark for various computer vision applications involving camouflaged patterns, such as agricultural, industrial, and medical scenarios. Code is available at https://github.com/pursuitxi/Context-measure.