Aarhus University Seal / Aarhus Universitets segl

Weed classification using explainable multi-resolution slot attention

Publikation: Bidrag til tidsskrift/Konferencebidrag i tidsskrift /Bidrag til avisTidsskriftartikelForskningpeer review


In agriculture, explainable deep neural networks (DNNs) can be used to pinpoint the discriminative part of weeds for an imagery classification task, albeit at a low resolution, to control the weed population. This paper proposes the use of a multi-layer attention procedure based on a transformer combined with a fusion rule to present an interpretation of the DNN decision through a high-resolution attention map. The fusion rule is a weighted average method that is used to combine attention maps from different layers based on saliency. Attention maps with an explanation for why a weed is or is not classified as a certain class help agronomists to shape the high-resolution weed identification keys (WIK) that the model perceives. The model is trained and evaluated on two agricultural datasets that contain plants grown under different conditions: the Plant Seedlings Dataset (PSD) and the Open Plant Phenotyping Dataset (OPPD). The model represents attention maps with highlighted requirements and information about misclassification to enable cross-dataset evaluations. State-of-the-art comparisons represent classification developments after applying attention maps. Average accuracies of 95.42% and 96% are gained for the negative and positive explanations of the PSD test sets, respectively. In OPPD evaluations, accuracies of 97.78% and 97.83% are obtained for negative and positive explanations, respectively. The visual comparison between attention maps also shows high-resolution information.
Antal sider18
StatusUdgivet - 9 okt. 2021

Bibliografisk note

Funding Information:
Funding: This research was funded by the Green Development and Demonstration Program (GUDP) under the Danish Ministry for Food, Agriculture, and Fisheries (project: Square Meter Farming (SqM-Farm), journal number: 34009-17-1303).

Publisher Copyright:
© 2021 by the authors. Licensee MDPI, Basel, Switzerland.

Se relationer på Aarhus Universitet Citationsformater

ID: 224189593