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

2025-02-26

AI Summary

Tree species identification urgently requires interpretable vision models, yet existing XAI methods struggle to effectively characterize global texture attributes—such as roughness and smoothness—in bark imagery: local-feature-based approaches lack global semantic coherence, while external concept-set-driven methods suffer from high annotation cost and subjectivity. This paper proposes a lightweight post-hoc explanation framework that, for the first time, enables concept-based interpretation of tree species classifiers using quantifiable global visual concepts—e.g., roughness derived from Gray-Level Co-occurrence Matrix (GLCM) statistics—without requiring external concept datasets. Our method jointly evaluates concept importance and model reasoning via operator-driven concept activation analysis and Kendall’s Tau-based consistency validation. On human-annotated benchmarks, it significantly outperforms TCAV and Llama3.2, demonstrating superior alignment with human perceptual judgment.

Technology Category

• Computer Vision: Interpretability, Explainability, and Transparency
• Humans and AI: Explainable AI (XAI) for Human Understanding
• Machine Learning: Transparent, Interpretable, Explainable ML

Application Category

• User Modeling, Personalization and Recommendation: Explainable and interpretable methods for personalization
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• Search and Retrieval-Augmented AI: Web query analysis, representation and understanding

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.

Problem

• Enhancing interpretability of tree species classification
• Quantifying global visual features in bark images
• Reducing computational overhead in XAI methods

Innovation

• Lightweight post-hoc explainable method
• Quantifiable global visual concepts
• Reduced computational overhead