ConvNeXt based semi-supervised approach with consistency regularization for weeds classification

On the 1st of November 2023, an article linked to the project DESHERBROB has been published in the scientific review “Expert systems with Applications” and posted on the website ScienceDirect.

The aim of the research team is to develop robust and precise deep learning models, to carry-out the recognition and identification of weed species, using both types of data. To this end, it proposes a method, that adopts the semi-supervised learning paradigm, to optimally combine labeled and unlabeled data. The method is based on a new deep neural networks architecture, which consists of a modernized convolutional encoder belonging to the family ConvNeXt and a thoroughly designed deep decoder network. This architecture, enables a successful integration of consistency regularization.

Here is the link to read the whole article :

by Farouk Benchallal, Adel Hafiane, Nicolas Ragot and Raphael Canals

Key words : Semi-supervised learning, Deep learning, Consistency regularization, Precision agriculture