Detail publikačního výsledku

Multi-Head Attention-Based Transfer Learning Approach for Potato Disease Detection

MYŠKA, V.; MEZINA, A.; VANĚK, P.; BURGET, R.; GENZOR, S.; MIZERA, J.; ŠTÝBNAR, M.; KIAC, M.; FROLKA, J.

Originální název

Multi-Head Attention-Based Transfer Learning Approach for Potato Disease Detection

Anglický název

Multi-Head Attention-Based Transfer Learning Approach for Potato Disease Detection

Druh

Stať ve sborníku v databázi WoS či Scopus

Originální abstrakt

Potatoes are widely consumed all over the world. Being one of the most cultivated crops around the world, they also attract various diseases. Hence, the early identification of such diseases using machine learning-based automated methods, is necessary. In this paper, the solution for the early detection of two most commonly occurring diseases in potato leaves, i.e. Early blight and Late blight have been proposed. In this work, a VGG16 model has been fine-tuned with a multihead attention layer for identifying useful patterns for the classification of potato plant leaf diseases. The multi-head attention mechanism is useful since it can capture the relationship that exists in different parts of an input potato disease leaf image. The proposed model has attained an accuracy of 91% with an F1-score of 0.9103. The better performance of the proposed model is a testimony to its effectiveness in the early identification of potato leaf disease.

Anglický abstrakt

Potatoes are widely consumed all over the world. Being one of the most cultivated crops around the world, they also attract various diseases. Hence, the early identification of such diseases using machine learning-based automated methods, is necessary. In this paper, the solution for the early detection of two most commonly occurring diseases in potato leaves, i.e. Early blight and Late blight have been proposed. In this work, a VGG16 model has been fine-tuned with a multihead attention layer for identifying useful patterns for the classification of potato plant leaf diseases. The multi-head attention mechanism is useful since it can capture the relationship that exists in different parts of an input potato disease leaf image. The proposed model has attained an accuracy of 91% with an F1-score of 0.9103. The better performance of the proposed model is a testimony to its effectiveness in the early identification of potato leaf disease.

Klíčová slova

Plant disease classification, Deep Learning, Multi-head attention, VGG16, Transfer learning

Klíčová slova v angličtině

Plant disease classification, Deep Learning, Multi-head attention, VGG16, Transfer learning

Autoři

MYŠKA, V.; MEZINA, A.; VANĚK, P.; BURGET, R.; GENZOR, S.; MIZERA, J.; ŠTÝBNAR, M.; KIAC, M.; FROLKA, J.

Rok RIV

2026

Vydáno

30.10.2023

Místo

Gent

ISBN

979-8-3503-9328-6

Kniha

2023 15th International Congress on Ultra Modern Telecommunications and Control Systems and Workshops (ICUMT)

Strany od

165

Strany do

169

Strany počet

4

BibTex

@inproceedings{BUT185640,
  author="Radim {Burget} and Martin {Kiac} and Rudra {Shaurya} and Ritesh {Mauya} and Malay Kishore {Dutta}",
  title="Multi-Head Attention-Based Transfer Learning Approach for Potato Disease Detection",
  booktitle="2023 15th International Congress on Ultra Modern Telecommunications and Control Systems and Workshops (ICUMT)",
  year="2023",
  pages="165--169",
  address="Gent",
  isbn="979-8-3503-9328-6"
}