# Cotton leaf disease detection model focusing on small targets and comprehensive feature extraction

## TL;DR

This paper introduces a new model for detecting small leaf disease spots on cotton plants, achieving high accuracy and better performance than existing methods.

## Contribution

The novel CM-YOLO model integrates SS2D and MSDA modules for improved small target detection in cotton leaf disease identification.

## Key findings

- CM-YOLO achieves an mAP50 of 0.933 and a recall of 0.891 for cotton leaf disease detection.
- The model outperforms YOLOv8n and YOLOv11n in terms of detection accuracy for small targets.
- CM-YOLO shows strong generalization across different plant datasets.

## Abstract

Cotton, as a globally important economic crop, requires early and accurate disease detection to ensure stable yield and promote sustainable development. However, due to the small size of certain leaf lesions, traditional detection methods often suffer from missed or false detections. To address this issue, we propose an improved YOLOv8-based model, CM-YOLO, aimed at enhancing the detection performance for small cotton leaf disease targets. Specifically, the SS2D module from VMamba is introduced into the backbone network to achieve comprehensive feature extraction through multi-directional scanning. Furthermore, the MSDA module is embedded prior to the SPPF module to reduce performance degradation caused by redundant computations and to enhance the model’s focus on critical small targets. Finally, the original bounding box loss function is replaced with DIoU, enabling precise localization of small targets by optimizing anchor center point distances and accelerating model convergence. Experimental results demonstrate that CM-YOLO achieves superior performance in cotton leaf disease detection, with an mAP50 of 0.933 and a recall of 0.891. Compared with state-of-the-art methods, YOLOv8n and YOLOv11n achieve mAP50 values of 0.874 and 0.930, respectively, both lower than CM-YOLO, thereby validating the effectiveness of the proposed method. Additionally, generalization experiments indicate that the model maintains high detection accuracy and robustness across different plant datasets, highlighting its strong applicability in complex scenarios and providing a valuable reference for intelligent agricultural disease detection research.