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

2026-01-23

AI Summary

This work addresses the challenges of few-shot learning and class confusion in fine-grained tree species classification, which arise from long-tailed data distributions and high inter-class similarity. Inspired by the human practice of consulting domain experts to overcome cognitive limitations, we propose EKDC-Net, a lightweight, plug-and-play expert knowledge-guided decision calibration network. EKDC-Net dynamically integrates discriminative knowledge from external “domain experts” through a Local Prior-guided Knowledge Extraction Module (LPKEM) and an Uncertainty-guided Decision Calibration Module (UDCM). We also introduce CU-Tree102, a large-scale dataset comprising 102 tree species. Evaluated on three benchmarks, our method achieves state-of-the-art performance with only a 0.08M parameter increase, improving the backbone network’s accuracy and precision by 6.42% and 11.46%, respectively.

Technology Category

Machine Learning: Calibration & Uncertainty QuantificationData Mining & Knowledge Management: Knowledge Acquisition from the WebConstraint Satisfaction and Optimization: Constraint Learning and Acquisition

Application Category

Economics, Online Markets and Human Computation: Data quality aspects of human-annotated datasetsSearch and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for rankingGraph Algorithms and Modeling for the Web: Graph neural networks and deep learning approaches for Web-related graphs

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.

Problem

• fine-grained classification
• long-tailed distribution
• inter-class similarity
• few-shot categories
• tree species classification

Innovation

• Expert Knowledge Guidance
• Decision Calibration
• Uncertainty-Aware Learning
• Fine-Grained Classification
• Plug-and-Play Module