Portal de Periódicos da CAPES

Artigo Acesso aberto Produção Nacional Revisado por pares

BIBTEX RIS

Pseudo-label semi-supervised learning for soybean monitoring

2023; Elsevier BV; Volume: 4; Linguagem: Inglês

10.1016/j.atech.2023.100216

2772-3755

Gabriel Kirsten Menezes, Gilberto Astolfi, José Augusto Correa Martins, Everton Castel�ão Tetila, Adair da Silva Oliveira, Diogo Nunes Gonçalves, José Marcato, Jonathan de Andrade Silva, Jonathan Li, Wesley Nunes Gonçalves, Hemerson Pistori,

Spectroscopy and Chemometric Analyses

This paper presents a semi-supervised learning method based on superpixels and convolutional neural networks (CNNs) to assign and improve the identification of weeds in soybean crops. Despite its promising results, CNNs require massive amounts of labeled training data to learn, so we intend to improve the manual labeling phase with an automated pseudo-labeling process. We propose a method that uses an additional phase of mini-batch processing to fine-tune and assign pseudo labels to the images based on previously annotated SLIC segmentation during the algorithm training phase. This research paper shows that the proposed method improves the soybean monitoring accuracy compared with the traditionally trained methods using a tiny amount of labeled superpixels. There was an increase in the training time, but this is an expected result and even preferable to doing manual label annotation..