PALM-Net: Population-aware leaf disease multilinear network for robust plant disease detection

Plant disease detection systems are accurate on laboratory datasets, but struggle to maintain high accuracy in real field settings because of the variability in the environment, background noise, changes in lighting, and the diversity of plant species in terms of morphology. The similar disease pattern in the leaves are also challenging in the CNN-based models due to Global Average Pooling (GAP), which discards the spatial information that is specific to the lesion for the classification. The solution to this is inter-subject training which leads to population based tensor of the features. The tensor-based methods are based on frozen deep learning features and fail to take advantage of population-level disease distribution. The gap between the lab and the field is a continuous one and hinders the application in precision agriculture. A population-aware multilinear learning framework, PALM-Net, is proposed that consists of three components which groups features into a 4th-order population tensor, and supports spectral decorrelation and class-sensitive Discriminant Projection (DP) simultaneously. The experimental evaluation is carried out on the PlantVillage (54,305 images, 38 classes) dataset, Cassava Leaf Disease (26,220 images, 5 classes) dataset, and Tomato Disease (22,930 images, 10 classes) dataset. With only 12.07 million parameters, PALM-Net obtained a Top-1 accuracy of 99.32% on the PlantVillage dataset, 84.56% on the Cassava dataset, and 97.44% on the Tomato dataset. The proposed method also reduces the number of parameters by the proposed spectral decorrelation, allowing for stable multilinear optimisation and compression of the classifiers’ heads without compromising the classifiers’ discriminative performance.

Authors

Institutions

Publication Details

Journal
Journal of King Saud University - Computer and Information Sciences
Published
2026-11-18
DOI
https://doi.org/10.1007/s44443-026-01373-3
Primary Topic
Smart Agriculture and AI
Type
article
Field-Weighted Citation Impact
0.00

Funders

Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
NOV
article

PALM-Net: Population-aware leaf disease multilinear network for robust plant disease detection

Nilesh R. Marathe, Bhawani Singh Rathore, Mayank Kumar Jain, Vineeta Singh et al.
4 links
Journal of King Saud University - Computer and Information Sciences
Smart Agriculture and AI
article

PALM-Net: Population-aware leaf disease multilinear network for robust plant disease detection

Nilesh R. Marathe, Bhawani Singh Rathore, Mayank Kumar Jain, Vineeta Singh, Jong-Ha Lee
article en

Abstract

Plant disease detection systems are accurate on laboratory datasets, but struggle to maintain high accuracy in real field settings because of the variability in the environment, background noise, changes in lighting, and the diversity of plant species in terms of morphology. The similar disease pattern in the leaves are also challenging in the CNN-based models due to Global Average Pooling (GAP), which discards the spatial information that is specific to the lesion for the classification. The solution to this is inter-subject training which leads to population based tensor of the features. The tensor-based methods are based on frozen deep learning features and fail to take advantage of population-level disease distribution. The gap between the lab and the field is a continuous one and hinders the application in precision agriculture. A population-aware multilinear learning framework, PALM-Net, is proposed that consists of three components which groups features into a 4th-order population tensor, and supports spectral decorrelation and class-sensitive Discriminant Projection (DP) simultaneously. The experimental evaluation is carried out on the PlantVillage (54,305 images, 38 classes) dataset, Cassava Leaf Disease (26,220 images, 5 classes) dataset, and Tomato Disease (22,930 images, 10 classes) dataset. With only 12.07 million parameters, PALM-Net obtained a Top-1 accuracy of 99.32% on the PlantVillage dataset, 84.56% on the Cassava dataset, and 97.44% on the Tomato dataset. The proposed method also reduces the number of parameters by the proposed spectral decorrelation, allowing for stable multilinear optimisation and compression of the classifiers’ heads without compromising the classifiers’ discriminative performance.

Journal of King Saud University - Computer and Information SciencesVol. 38(10)
Dwarkadas J. Sanghvi College of Engineering (IN), Chhatrapati Shahu Ji Maharaj University (IN), Bennett University (IN), Keimyung University (KR), Manipal University Jaipur (IN)
Korea Health Industry Development Institute, Ministry of Education, India, Ministry of SMEs and Startups, Ministry of Science and ICT, South Korea, Commercializations Promotion Agency for R and D Outcomes
Zero hunger
Smart Agriculture and AI
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.

Laika access coming soon