CLAP Convolutional Lightweight Autoencoder for Plant Disease Classification

2026-02-21

AI Summary

This study addresses the challenge of accurately identifying subtle symptoms in field-acquired plant disease images, which traditional models often fail to capture. To this end, the authors propose CLAP, a lightweight convolutional autoencoder that employs depthwise separable convolutions to construct its encoder–decoder architecture and incorporates a Sigmoid-gated mechanism to enhance feature discriminability. The model further integrates multi-scale features from both encoder and decoder paths for classification. With only 5 million parameters, CLAP achieves a training time of 20 milliseconds per image and an inference latency of 1 millisecond, maintaining remarkably low computational overhead while delivering state-of-the-art or competitive accuracy across multiple public plant disease datasets. This approach significantly improves the detection of fine-grained pathological features in real-world agricultural settings.

Technology Category

• Machine Learning: Deep Generative Models & Autoencoders
• Computer Vision: Large Vision Models
• Search and Optimization: Learning to Search

Application Category

• Search and Retrieval-Augmented AI: Efficiency and scalability of Web search engines
• Web Mining and Content Analysis: Large pretrained models with web data
• Responsible Web: Machine-in-the-loop, human agency and autonomy

Abstract

Convolutional neural networks have remarkably progressed the performance of distinguishing plant diseases, severity grading, and nutrition deficiency prediction using leaf images. However, these tasks become more challenging in a realistic in-situ field condition. Often, a traditional machine learning model may fail to capture and interpret discriminative characteristics of plant health, growth and diseases due to subtle variations within leaf subcategories. A few deep learning methods have used additional preprocessing stages or network modules to address the problem, whereas several other methods have utilized pre-trained backbone CNNs, most of which are computationally intensive. Therefore, to address the challenge, we propose a lightweight autoencoder using separable convolutional layers in its encoder decoder blocks. A sigmoid gating is applied for refining the prowess of the encoders feature discriminability, which is improved further by the decoder. Finally, the feature maps of the encoder decoder are combined for rich feature representation before classification. The proposed Convolutional Lightweight Autoencoder for Plant disease classification, called CLAP, has been experimented on three public plant datasets consisting of cassava, tomato, maize, groundnut, grapes, etc. for determining plant health conditions. The CLAP has attained improved or competitive accuracies on the Integrated Plant Disease, Groundnut, and CCMT datasets balancing a tradeoff between the performance, and little computational cost requiring 5 million parameters. The training time is 20 milliseconds and inference time is 1 ms per image.

Problem

• plant disease classification
• in-situ field condition
• leaf image analysis
• subtle variation
• computational efficiency

Innovation

• lightweight autoencoder
• separable convolution
• sigmoid gating
• plant disease classification
• feature fusion