LANet: Enhancing Plant Disease Recognition Through Transfer Learning and Layer Attention

XIN LEI, ARDHENDU BEHERA, Wuping Zhang, Yang Sun, YONGHUAI LIU

Research output: Chapter in Book/Report/Conference proceedingConference proceeding (ISBN)peer-review

Abstract

Accurate recognition of plant diseases plays a critical
role in maintaining agricultural productivity and food
security. This study proposes LANet, an innovative network
architecture aimed at improving the precision of identifying
and categorizing plant diseases from images. LANet consists
of two primary components. Firstly, Layer Attention applies
self-attention across feature layers at different scales to capture
the weights between cross-scale features, addressing the
data loss caused by downsampling and enhancing plant species
recognition. Secondly, we introduce a transfer learning method,
where a plant species classification network is initially trained,
its parameters are then frozen, and several convolutional layers
are added to train the disease classification network. This allows
the model to leverage the learned classification information for
more accurate disease recognition. Our model demonstrates
an accuracy of 85.62%, outperforming nine other models significantly.
Comparative analyses using the public PlantVillage
dataset highlight the superior performance of our method in
disease recognition.
Original languageEnglish
Title of host publicationProceedings of The Sixth IEEE international conference on Image Processing Applications and Systems
PublisherIEEE Explore
Publication statusAccepted/In press - 19 Sept 2024
EventThe Sixth IEEE international conference on Image Processing Applications and Systems - Lyon , France
Duration: 9 Jan 202511 Jan 2025

Conference

ConferenceThe Sixth IEEE international conference on Image Processing Applications and Systems
Abbreviated titleIPAS
Country/TerritoryFrance
CityLyon
Period9/01/2511/01/25

Fingerprint

Dive into the research topics of 'LANet: Enhancing Plant Disease Recognition Through Transfer Learning and Layer Attention'. Together they form a unique fingerprint.

Cite this