[论文] AgroVisNet: A lightweight Convolutional Network and the BD-PlantDX Expert-Validated Benchmark for Radish, Potato and Pointed Gourd Disease Classification (arXiv:2609.10469)

论文概要

研究领域: CV
作者: Md. Abdullah Mandal, Saad Ahmed, Md. Khalid Syfullah
发布时间: 2026-09-09
arXiv: 2609.10469

中文摘要

自动化植物病害诊断越来越多地部署在农民手持设备上，但公共基准被少数非本地作物主导，区域特定数据集很少经过领域专家验证，达到竞争精度的架构参数量不适合低成本硬件。本文提出AgroVisNet，一种从头训练的紧凑卷积网络，以及BD-PlantDX——一个专家验证的基准，包含12,432张田间图像，涵盖孟加拉国Bogura和Nilphamari地区收集的萝卜、马铃薯和尖瓜的12类健康和病害状态。AgroVisNet仅290,572个可训练参数，在BD-PlantDX上达到99.52%测试准确率和加权F1，超过所有六个ImageNet预训练轻量级主干网络，同时参数量少8.7到16.8倍。量化为0.46MB全整数网络后仅损失0.22个百分点准确率，在单CPU上8.40ms分类一张图像。

原文摘要

Automated plant disease diagnosis is increasingly deployed on farmer-held devices in regions where agronomic expertise is scarce and network connectivity is unreliable. Three obstacles limit its practical value: public benchmarks are dominated by a small set of non-native crops, region-specific datasets are rarely validated by domain experts, and the architectures that reach competitive accuracy carry parameter budgets that are unsuited to low-cost hardware. We propose AgroVisNet, a compact convolutional network trained from scratch, together with BD-PlantDX, an expert-validated benchmark of 12,432 field images spanning 12 classes of radish, potato and pointed gourd in healthy and diseased states, collected across the Bogura and Nilphamari districts of Bangladesh. AgroVisNet couples grouped bottleneck residual blocks carrying sequential channel and spatial attention with multi-scale depthwise blocks and a dual-pooling classification head, reaching 290,572 trainable parameters. On BD-PlantDX the model attains 99.52% test accuracy and 99.52% weighted F1, exceeding all six ImageNet-pretrained lightweight backbones evaluated under an identical protocol while using 8.7 to 16.8 times fewer parameters and 1.3 to 8.5 times fewer multiply-accumulate operations. Exported for deployment, the model quantises to a 0.46 MB full-integer network at a 0.22 percentage-point accuracy cost and classifies an image in 8.40 ms on a single CPU. Across five random seeds accuracy remains at 99.57 +- 0.10%, a ten-variant ablation isolates the contribution of each component, and the same architecture transfers without redesign to two independently collected datasets at 98.71% and 99.05% accuracy. Grad-CAM evidence indicates that predictions rest on lesion-bearing leaf regions rather than on background cues.

自动采集于 2026-09-11

#论文 #arXiv #CV #小凯