Cross-Dataset Generalization of Bangladeshi Rice Leaf Disease Classifiers: Benchmark, Diagnosis, and Mitigation

Deep learning models for crop leaf disease recognition routinely report near-perfect accuracy yet are typically trained and evaluated on a single dataset collected under controlled laboratory conditions, leaving their behavior under realistic cross-region domain shift poorly understood. We introduce MLD (Multi-crop Leaf Disease) dataset, a unified multi-region benchmark that combines six public crop-disease datasets from the USA, Asia, and Africa into a shared hierarchical taxonomy spanning 18 crops, 56 crop-disease classes (including one healthy class per crop) making 167,427 images. We define standardized single-source and pooled multi-source evaluation protocols that explicitly probe cross-region generalization. We also investigate whether exploiting the inherent crop-to-disease dependency via a hierarchical formulation (HiLeaD) that conditions disease prediction on the predicted crop improves recognition under cross-region shift. Under the HiLeaD, the model trained on PlantVillage achieves 99.07% in-domain disease F1 but collapses to 12.88% when tested on PlantDoc, exposing a severe cross-region domain gap. The model trained on the pooled MLD dataset partly recovers cross-region disease F1 from 12.88% to 39.64% on PlantDoc (HiLeaD), achieving a 26.76 percentage point improvement. The hierarchical formulation provides a consistent additional gain, ranging from 1.71 to 4.88 percentage points in disease F1 over the flat baseline under the MLD dataset indicating that progress in this area is currently limited more by data coverage and diversity than by model design.

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.

Reliable crop disease detection requires models that perform consistently across diverse acquisition conditions, yet existing evaluations often focus on single architectural families or lab-generated datasets. This work presents a systematic empirical comparison of three model paradigms for fine-grained crop disease classification: Convolutional Neural Networks (CNNs), contrastive Vision-Language Models (VLMs), and generative VLMs. To enable controlled analysis of domain effects, we introduce AgriPath-LF16, a benchmark of 111k images spanning 16 crops and 41 diseases with explicit separation between laboratory and field imagery, alongside a balanced 30k subset for standardised training and evaluation. We train and evaluate all models under unified protocols across full, lab-only, and field-only training regimes using macro-F1 and Parse Success Rate (PSR) to account for generative reliability (i.e., output parsability measured via PSR). The results reveal distinct performance profiles: CNNs achieve the highest accuracy on in-domain imagery but exhibit pronounced degradation under domain shift; contrastive VLMs provide a robust and parameter-efficient alternative with competitive cross-domain performance; generative VLMs demonstrate the strongest resilience to distributional variation, albeit with additional failure modes stemming from free-text generation. These findings highlight that architectural choice should be guided by deployment context rather than aggregate performance alone.