Frequency-domain attention enhanced YOLOv11-EfficientFormerV2 for Tiny lesion detection in complex field plant images.

Abstract

Introduction To address the challenges of low detection precision, severe background interference, and high model complexity in tiny crop disease lesion detection (defined as lesions occupying 8×8 to 32×32 pixels at 640×640 input resolution) under complex field environments, this study proposes a lightweight detection model named FDA-YOLO by integrating frequency-domain attention and improved YOLOv11. Methods The model employs EfficientFormerV2 as the backbone to extract multi-scale features with low computational cost, and introduces a frequency domain attention module to enhance high-frequency tiny disease lesion details and suppress background noise. Results Comprehensive experiments on the PlantDoc dataset demonstrate that the proposed model achieves 96.3% mAP@0.5, 96.8% precision, and 36.4 FPS with only 28.5M parameters, outperforming the selected baseline detectors under the adopted experimental setting. Discussion The model realizes an optimal balance between accuracy, efficiency, and lightweight performance, providing a reliable and practical solution for real-time tiny lesion detection inprecision agriculture and edge device deployment.

Plant phenotyping relevance

植物病斑という植物の病態を画像から検出するモデルを開発し、PlantDocデータセットで精度・速度・計算量を比較検証しているため、植物フェノタイピング手法が中心である。

Code and data availability

The supplied blocks describe experiments on the public PlantDoc dataset, but PlantDoc is a cited prior-work dataset (Singh et al., 2020), not a paper-specific asset of this study. No data availability statement, code deposit, model checkpoint release, or author-provided public URL for the FDA-YOLO implementation, split

No evidence-backed public reproduction asset is currently recorded.