Redirigiendo al acceso original de articulo en 15 segundos...
Inicio  /  Agriculture  /  Vol: 14 Par: 2 (2024)  /  Artículo
ARTÍCULO
TITULO

Wheat Teacher: A One-Stage Anchor-Based Semi-Supervised Wheat Head Detector Utilizing Pseudo-Labeling and Consistency Regularization Methods

Rui Zhang    
Mingwei Yao    
Zijie Qiu    
Lizhuo Zhang    
Wei Li and Yue Shen    

Resumen

Wheat breeding heavily relies on the observation of various traits during the wheat growth process. Among all traits, wheat head density stands out as a particularly crucial characteristic. Despite the realization of high-throughput phenotypic data collection for wheat, the development of efficient and robust models for extracting traits from raw data remains a significant challenge. Numerous fully supervised target detection algorithms have been employed to address the wheat head detection problem. However, constrained by the exorbitant cost of dataset creation, especially the manual annotation cost, fully supervised target detection algorithms struggle to unleash their full potential. Semi-supervised training methods can leverage unlabeled data to enhance model performance, addressing the issue of insufficient labeled data. This paper introduces a one-stage anchor-based semi-supervised wheat head detector, named ?Wheat Teacher?, which combines two semi-supervised methods, pseudo-labeling, and consistency regularization. Furthermore, two novel dynamic threshold components, Pseudo-label Dynamic Allocator and Loss Dynamic Threshold, are designed specifically for wheat head detection scenarios to allocate pseudo-labels and filter losses. We conducted detailed experiments on the largest wheat head public dataset, GWHD2021. Compared with various types of detectors, Wheat Teacher achieved a mAP0.5 of 92.8% with only 20% labeled data. This result surpassed the test outcomes of two fully supervised object detection models trained with 100% labeled data, and the difference with the other two fully supervised models trained with 100% labeled data was within 1%. Moreover, Wheat Teacher exhibits improvements of 2.1%, 3.6%, 5.1%, 37.7%, and 25.8% in mAP0.5 under different labeled data usage ratios of 20%, 10%, 5%, 2%, and 1%, respectively, validating the effectiveness of our semi-supervised approach. These experiments demonstrate the significant potential of Wheat Teacher in wheat head detection.

 Artículos similares

       
 
Vesna ?upunski, Radivoje Jevtic, Milosav Grcak, Mirjana Lalo?evic, Branka Orbovic, Dalibor ?ivanov and Desimir Kne?evic    
Tracking the distribution of Fusarium species and the detection of changes in toxin production provides epidemiological information that is essential for Fusarium head blight (FHB) management. Members of Fusarium graminearum species complex (FGSC) were c... ver más
Revista: Agriculture

 
Elisane W. Tessmann and David A. Van Sanford    
-
Revista: Agronomy

 
Alex P. Whan, Arunas P. Verbyla, Jos C. Mieog, Crispin A. Howitt and Jean-Philippe Ral    
In glasshouse studies we have previously shown that endosperm-specific RNAi suppression of the primary starch phosphorylation enzyme, Glucan, Water Dikinase (GWD) leads to enhanced early vigor, greater leaf biomass, and increases in both head size and yi... ver más
Revista: Agronomy

 
Firas Talas, Rasha Kalih, and Thomas Miedaner     Pág. 128 - 134
Revista: PHYTOPATHOLOGY

 
A. B. Kriss, P. A. Paul, and L. V. Madden     Pág. 867 - 877
Revista: PHYTOPATHOLOGY