Next Article in Journal
Design, Manufacturing, and Control of a Pneumatic-Driven Passive Robotic Gait Training System for Muscle-Weakness in a Lower Limb
Next Article in Special Issue
Detecting Animal Contacts—A Deep Learning-Based Pig Detection and Tracking Approach for the Quantification of Social Contacts
Previous Article in Journal
High Dynamic Weak Signal Tracking Algorithm of a Beidou Vector Receiver Based on an Adaptive Square Root Cubature Kalman Filter
Previous Article in Special Issue
Orchard Mapping with Deep Learning Semantic Segmentation
 
 
Article

Weed Classification Using Explainable Multi-Resolution Slot Attention

Department of Electrical and Computer Engineering, Aarhus University, 8200 Aarhus, Denmark
*
Author to whom correspondence should be addressed.
Academic Editors: Asim Biswas, Dionysis Bochtis and Aristotelis C. Tagarakis
Sensors 2021, 21(20), 6705; https://doi.org/10.3390/s21206705
Received: 30 June 2021 / Revised: 30 September 2021 / Accepted: 1 October 2021 / Published: 9 October 2021
(This article belongs to the Collection Sensors and Robotics for Digital Agriculture)
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. View Full-Text
Keywords: transformer; slot attention; explainable neural network; fusion rule; weed classification; weed identification key; precision agriculture transformer; slot attention; explainable neural network; fusion rule; weed classification; weed identification key; precision agriculture
Show Figures

Figure 1

MDPI and ACS Style

Farkhani, S.; Skovsen, S.K.; Dyrmann, M.; Jørgensen, R.N.; Karstoft, H. Weed Classification Using Explainable Multi-Resolution Slot Attention. Sensors 2021, 21, 6705. https://doi.org/10.3390/s21206705

AMA Style

Farkhani S, Skovsen SK, Dyrmann M, Jørgensen RN, Karstoft H. Weed Classification Using Explainable Multi-Resolution Slot Attention. Sensors. 2021; 21(20):6705. https://doi.org/10.3390/s21206705

Chicago/Turabian Style

Farkhani, Sadaf, Søren Kelstrup Skovsen, Mads Dyrmann, Rasmus Nyholm Jørgensen, and Henrik Karstoft. 2021. "Weed Classification Using Explainable Multi-Resolution Slot Attention" Sensors 21, no. 20: 6705. https://doi.org/10.3390/s21206705

Find Other Styles
Note that from the first issue of 2016, MDPI journals use article numbers instead of page numbers. See further details here.

Article Access Map by Country/Region

1
Back to TopTop