Enhance-YOLOv8: a robust small-object detection framework for complex agricultural pest scenarios
TL;DR
This work proposes Enhance-YOLOv8, which replaces YOLOv8's Cross Stage Partial with 2 convolutions (C2f) backbone module with Enhance Adaptive Fine-grained Channel Attention (Enhance_AFCA), which integrates hierarchical multi-scale feature extraction and adaptive edge enhancement to address edge information loss and inadequate feature fusion.
Abstract
Agricultural pest detection is constrained by three critical challenges: small pest size causing feature loss, complex backgrounds ( e.g ., foliage and lighting) hindering feature extraction, and severe class imbalance (pests occupying <5% of image pixels), limiting standard detectors like You Only Look Once version 8 (YOLOv8). To overcome these, we propose Enhance-YOLOv8, which replaces YOLOv8's Cross Stage Partial with 2 convolutions (C2f) backbone module with Enhance Adaptive Fine-grained Channel Attention (Enhance_AFCA). This module integrates hierarchical multi-scale feature extraction and adaptive edge enhancement to address edge information loss and inadequate feature fusion. Its adaptive fine-grained channel attention dynamically weights informative channels while suppressing noise, reducing bias from class imbalance. A novel MANet_Pest Detection (MANet_PD) module in the neck network enhances multi-scale feature fusion, improving small-target detection. The model further adopts Wise Intersection over Union (WiseIoU) Loss with Inner-Focaler-ShapeIoU, accelerating convergence and refining localization via auxiliary bounding boxes and dynamic penalties. Experimental results demonstrate that Enhance-YOLOv8 achieves a mAP@0.5 of 93.5% on our custom dataset and 77.3% on the public AgroPest-12 dataset, representing improvements of 2.8 percentage points and 3.0 percentage points over YOLOv8, respectively. The model exhibits robust performance in complex agricultural scenarios and demonstrates strong potential for deployment in precision agriculture.