Crown-CAM: Interpretable Visual Explanations for Tree Crown Detection in Aerial Images

TL;DR

Crown-CAM is a novel interpretable visualization method for tree crown detection in aerial images, improving localization accuracy and explanation reliability over existing methods using unsupervised activation map selection and IoU-based metrics.

Contribution

The paper introduces Crown-CAM, an interpretable class activation mapping technique that enhances localization accuracy and explanation quality for tree crown detection in aerial imagery.

Findings

Crown-CAM outperforms existing methods in IoU metrics.

It provides reliable visual explanations for dense forest scenes.

Empirical results show significant improvement in explanation accuracy.

Abstract

Visual explanation of ``black-box'' models allows researchers in explainable artificial intelligence (XAI) to interpret the model's decisions in a human-understandable manner. In this paper, we propose interpretable class activation mapping for tree crown detection (Crown-CAM) that overcomes inaccurate localization & computational complexity of previous methods while generating reliable visual explanations for the challenging and dynamic problem of tree crown detection in aerial images. It consists of an unsupervised selection of activation maps, computation of local score maps, and non-contextual background suppression to efficiently provide fine-grain localization of tree crowns in scenarios with dense forest trees or scenes without tree crowns. Additionally, two Intersection over Union (IoU)-based metrics are introduced to effectively quantify both the accuracy and inaccuracy of generated explanations with respect to regions with or even without tree crowns in the image. Empirical evaluations demonstrate that the proposed Crown-CAM outperforms the Score-CAM, Augmented Score-CAM, and Eigen-CAM methods by an average IoU margin of 8.7, 5.3, and 21.7 (and 3.3, 9.8, and 16.5) respectively in improving the accuracy (and decreasing inaccuracy) of visual explanations on the challenging NEON tree crown dataset.