HieraEdgeNet: A Multi-Scale Edge-Enhanced Framework for Automated Pollen Recognition

TL;DR

HieraEdgeNet is a novel multi-scale edge-enhanced deep learning framework that significantly improves the accuracy and efficiency of automated pollen recognition by explicitly modeling edge features and fusing them with semantic information.

Contribution

This paper introduces HieraEdgeNet, a new multi-scale edge-enhancement framework with three modules, achieving state-of-the-art accuracy in pollen detection.

Findings

Achieves a mean Average Precision of 0.9501 on a large pollen dataset.

Outperforms baseline models like YOLOv12n and RT-DETR.

Provides more precise boundary-focused feature representations.

Abstract

Automated pollen recognition is vital to paleoclimatology, biodiversity monitoring, and public health, yet conventional methods are hampered by inefficiency and subjectivity. Existing deep learning models often struggle to achieve the requisite localization accuracy for microscopic targets like pollen, which are characterized by their minute size, indistinct edges, and complex backgrounds. To overcome this limitation, we introduce HieraEdgeNet, a multi-scale edge-enhancement framework. The framework's core innovation is the introduction of three synergistic modules: the Hierarchical Edge Module (HEM), which explicitly extracts a multi-scale pyramid of edge features that corresponds to the semantic hierarchy at early network stages; the Synergistic Edge Fusion (SEF) module, for deeply fusing these edge priors with semantic information at each respective scale; and the Cross Stage Partial Omni-Kernel Module (CSPOKM), which maximally refines the most detail-rich feature layers using an Omni-Kernel operator - comprising anisotropic large-kernel convolutions and mixed-domain attention - all within a computationally efficient Cross-Stage Partial (CSP) framework. On a large-scale dataset comprising 120 pollen classes, HieraEdgeNet achieves a mean Average Precision (mAP@.5) of 0.9501, significantly outperforming state-of-the-art baseline models such as YOLOv12n and RT-DETR. Furthermore, qualitative analysis confirms that our approach generates feature representations that are more precisely focused on object boundaries. By systematically integrating edge information, HieraEdgeNet provides a robust and powerful solution for high-precision, high-efficiency automated detection of microscopic objects.