# SS-OPDet: A Semi-Supervised Open-Set Detection Framework for Dead Pine Wood Detection

## TL;DR

This paper introduces SS-OPDet, a new framework for detecting dead pine wood using semi-supervised learning, improving accuracy and reducing annotation needs for managing pine wilt disease.

## Contribution

SS-OPDet is a novel semi-supervised open-set detection framework for dead pine wood with dynamic feature fusion and pseudo-label strategies.

## Key findings

- SS-OPDet achieved 84.73% average precision and 94.48% recall on 7733 UAV images.
- The framework showed robust performance with an Absolute Open-Set Error of 271 and a Wilderness Impact of 0.0917%.
- Cross-region validation confirmed the method's generalization and robustness.

## Abstract

Pine wilt disease poses a significant threat to pine forests worldwide, necessitating efficient and accurate detection of dead pine wood for effective disease control and forest management. Traditional deep learning methods based on supervised closed-set paradigms often struggle to address unknown interfering objects, causing false positives, missed detection, and increased annotation burdens. To overcome these challenges, we propose SS-OPDet, a semi-supervised open-set detection framework that leverages a small amount of labeled data along with abundant unlabeled data. SS-OPDet integrates a Weighted Multi-scale Feature Fusion module to dynamically integrate global- and local-scale features, thereby significantly improving representational accuracy for dead pine wood. Additionally, a Dynamic Confidence Pseudo-Label Generation strategy categorizes predictions by confidence level, effectively reducing training noise and maximizing the use of reliable unlabeled data. Experimental results from 7733 UAV images demonstrate that SS-OPDet achieves an average precision (APK) of 84.73%, a recall (RK) of 94.48%, an Absolute Open-Set Error (AOSE) of 271 and a Wilderness Impact (WI) of 0.0917%. Cross-region validation further confirms the robustness and generalization capability of the proposed framework. The proposed method offers a cost-effective and accurate solution for timely detection of pine wilt disease, providing substantial benefits to forest monitoring and management.