Expert Knowledge-Guided Decision Calibration for Accurate Fine-Grained Tree Species Classification

TL;DR

This paper introduces EKDC-Net, a knowledge-guided framework that leverages expert insights and uncertainty calibration to improve fine-grained tree species classification, especially under data scarcity and high class similarity.

Contribution

The paper proposes a novel expert knowledge-guided decision calibration network with modules for knowledge extraction and uncertainty-based decision correction, along with a new large-scale tree species dataset.

Findings

EKDC-Net achieves state-of-the-art accuracy on benchmark datasets.

The method improves backbone accuracy by 6.42% and precision by 11.46%.

The approach is lightweight, adding only 0.08M parameters.

Abstract

Accurate fine-grained tree species classification is critical for forest inventory and biodiversity monitoring. Existing methods predominantly focus on designing complex architectures to fit local data distributions. However, they often overlook the long-tailed distributions and high inter-class similarity inherent in limited data, thereby struggling to distinguish between few-shot or confusing categories. In the process of knowledge dissemination in the human world, individuals will actively seek expert assistance to transcend the limitations of local thinking. Inspired by this, we introduce an external "Domain Expert" and propose an Expert Knowledge-Guided Classification Decision Calibration Network (EKDC-Net) to overcome these challenges. Our framework addresses two core issues: expert knowledge extraction and utilization. Specifically, we first develop a Local Prior Guided Knowledge Extraction Module (LPKEM). By leveraging Class Activation Map (CAM) analysis, LPKEM guides the domain expert to focus exclusively on discriminative features essential for classification. Subsequently, to effectively integrate this knowledge, we design an Uncertainty-Guided Decision Calibration Module (UDCM). This module dynamically corrects the local model's decisions by considering both overall category uncertainty and instance-level prediction uncertainty. Furthermore, we present a large-scale classification dataset covering 102 tree species, named CU-Tree102 to address the issue of scarce diversity in current benchmarks. Experiments on three benchmark datasets demonstrate that our approach achieves state-of-the-art performance. Crucially, as a lightweight plug-and-play module, EKDC-Net improves backbone accuracy by 6.42% and precision by 11.46% using only 0.08M additional learnable parameters. The dataset, code, and pre-trained models are available at https://github.com/WHU-USI3DV/TreeCLS.