BarkXAI: A Lightweight Post-Hoc Explainable Method for Tree Species Classification with Quantifiable Concepts

TL;DR

BarkXAI introduces a lightweight, post-hoc explainability method for tree species classification that quantifies global visual features, improving interpretability and trust in bark-based models.

Contribution

This work is the first to explain bark vision models using global visual concepts with a lightweight, quantifiable approach that outperforms existing methods like TCAV and Llama3.2.

Findings

Significantly outperforms TCAV and Llama3.2 in concept importance ranking

Eliminates computational overhead in concept-based explanations

Enables quantification of complex visual concepts in bark images

Abstract

The precise identification of tree species is fundamental to forestry, conservation, and environmental monitoring. Though many studies have demonstrated that high accuracy can be achieved using bark-based species classification, these models often function as "black boxes", limiting interpretability, trust, and adoption in critical forestry applications. Attribution-based Explainable AI (XAI) methods have been used to address this issue in related works. However, XAI applications are often dependent on local features (such as a head shape or paw in animal applications) and cannot describe global visual features (such as ruggedness or smoothness) that are present in texture-dominant images such as tree bark. Concept-based XAI methods, on the other hand, offer explanations based on global visual features with concepts, but they tend to require large overhead in building external concept image datasets and the concepts can be vague and subjective without good means of precise quantification. To address these challenges, we propose a lightweight post-hoc method to interpret visual models for tree species classification using operators and quantifiable concepts. Our approach eliminates computational overhead, enables the quantification of complex concepts, and evaluates both concept importance and the model's reasoning process. To the best of our knowledge, our work is the first study to explain bark vision models in terms of global visual features with concepts. Using a human-annotated dataset as ground truth, our experiments demonstrate that our method significantly outperforms TCAV and Llama3.2 in concept importance ranking based on Kendall's Tau, highlighting its superior alignment with human perceptions.