Enhancing Cross-Grade Generalization in Banana Variety Classification via Hybrid CNN-Transformers and Knowledge Self-Distillation

Cross-dataset transfer in rice leaf disease classification remains a significant challenge, with models trained on one image collection performing substantially worse when deployed on another. We conduct a systematic benchmark across three Bangladeshi rice leaf disease datasets (5,419 images, 6 transfer pairs, 3 CNN backbones, 3 random seeds) to characterize and diagnose this failure. Strong augmentation recovers a mean cross-dataset macro-F1 improvement of +0.070 (Wilcoxon p < 0.001, 15 of 18 transfer pairs positive). Removing non-leaf image content via segmentation shows directional benefit (mean +0.066, p = 0.062, n = 36 paired observations) that is consistent across two independent segmentation methods but does not reach conventional significance. A self-supervised ViT control (DINOv2 linear probe) exhibits equivalent cross-dataset collapse to CNNs, ruling out architecture inductive bias as the primary driver and pointing to acquisition-condition shift. Adaptive batch normalization uniformly harms transfer performance, with harm magnitude correlating with source-target label-prior divergence and model depth (Spearman rho = 0.621, p = 0.009). Grad-CAM attribution analysis on 12 sampled predictions does not distinguish correct from incorrect cross-domain predictions (p = 0.462), indicating that common attribution proxies are insufficient for diagnosing shift at practical sample sizes. We document all frozen results, prespecified analysis criteria, and reproducibility artifacts in a public repository with SHA-256 integrity verification. This work establishes a rigorous empirical baseline for understanding cross-dataset generalization in agricultural computer vision and identifies both effective (augmentation) and ineffective (AdaBN) adaptation strategies.

Banana crop diseases threaten food security across the world, yet field diagnosis remains difficult because of limited expert access and visual similarity among disease classes. We present BananaVLM, a domain-adapted vision-language model for banana disease diagnosis built on LLaVA-v1.5-7B and fine-tuned with Low-Rank Adaptation (LoRA). To address the lack of multimodal agricultural instruction data, we introduce BananaInstruct, an automated pipeline that converts raw disease images into $\approx$80,000 question--answer pairs without manual annotation, using LLaVA-1.5-13B for symptom descriptions and Mistral-7B for agricultural Q&A generation and label grounding. Evaluated against 14 open-source and 5 closed-source VLMs on a nine-class benchmark, BananaVLM achieves 92.21% in-domain and 83.28% out-of-domain (OOD) classification accuracy, outperforming the best closed-source baseline, Gemini2.5Pro, by 49.8 and 63.3 percentage points, respectively. Binary healthy/diseased identification reaches 98.38% OOD accuracy with 1.00 recall. A controlled LoRA--DoRA comparison shows that DoRA performance degrades across epochs, while LoRA remains more effective for fine-grained classification. Qualitative evaluation using nine LLM judges yields G-Eval win rates of 0.81--0.96, while five domain experts prefer BananaVLM in 98.48% of 990 blind pairwise comparisons. These results show that lightweight domain adaptation with automated instruction tuning is an effective and scalable approach for specialized agricultural AI. Code, datasets, and model weights are available at https://github.com/samy101/banana-vlm

This work presents a new Hybrid Dense SwinV2, a two-branch framework that jointly leverages densely connected convolutional features and hierarchical customized Swin Transformer V2 (SwinV2) representations for cassava disease classification. The proposed framework captures high resolution local features through its DenseNet branch, preserving the fine structural cues and also allowing for effective gradient flow. Concurrently, the customized SwinV2 models global contextual dependencies through the idea of shifted-window self attention, which enables the capture of long range interactions critical in distinguishing between visually similar lesions. Moreover, an attention channel-squeeze module is employed for each CNN Transformer stream independently to emphasize discriminative disease related responses and suppress redundant or background driven activations. Finally, these discriminative channels are fused to achieve refined representations from the dense local and SwinV2 global correlated strengthened feature maps, respectively. The proposed Dense SwinV2 utilized a public cassava leaf disease dataset of 31000 images, comprised of five diseases, including brown streak, mosaic, green mottle, bacterial blight, and normal leaf conditions. The proposed Dense SwinV2 demonstrates a significant classification accuracy of 98.02 percent with an F1 score of 97.81 percent, outperforming well-established convolutional and transformer models. These results underline the fact that Hybrid Dense SwinV2 offers robustness and practicality in the field level diagnosis of cassava disease and real world challenges related to occlusion, noise, and complex backgrounds.