发表机构
Bahria University（巴里亚大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
CropCop构建了120类植物健康的可审计闭集识别系统，经基准重建与量化后，其ExecuTorch/XNNPACK构件在内部测试中达到高准确率与宏F1值，具备运行时保真度。
AI 中文摘要
植物健康评分看似精确，实则可能依赖重复图像族、长尾标签空间或从未被评估的运行时文件。本文提出CropCop，这是一个涵盖120个操作植物健康类别的闭集识别系统，拥有从语料库重建到最终量化构件直接执行的证据链。从117546张经审计的图像出发，我们确认了划分边界间存在3233个重复关系后，摒弃了继承的划分方案，冻结了一个包含109107张图像的基准，该基准在经审计的可信泄漏组间零交叉，且最大类与最小类的比例为151.7。完全微调后的DINOv3 ConvNeXt-Tiny参考模型在锁定的内部测试中达到98.51%的准确率和96.87%的宏F1值。紧凑的MobileNetV4 Conv-Medium衍生模型达到98.46%的准确率和96.27%的宏F1值，无需作为新蒸馏方法的证据。仅验证的后训练量化选择了带逐通道权重的动态激活，最终22.60 MiB的ExecuTorch/XNNPACK PTE在直接执行时达到98.46%的准确率和96.23%的宏F1值。在转换后的INT8图与PTE之间，16363个Top-1决策中仅有6个发生变化，配对分析显示存在适度的类平衡损失；探索性事后水果标签切片显示，召回率下降幅度大于总准确率所显示的程度。CropCop建立了严格的泄漏控制内部识别和软件运行时保真度，但未在未见过的农场、相机管线或物理Android硬件上建立性能。
英文摘要
A plant-health score can appear precise while resting on duplicated image families, a long-tailed label space, or a runtime file that was never evaluated. We present CropCop, a closed-set recognition system spanning 120 operational plant-health classes and an evidence chain from corpus reconstruction to direct execution of the final quantised artifact. Starting from 117,546 audited images, we rejected the inherited partition after confirming 3,233 duplicate relationships across split boundaries and froze a 109,107-image benchmark with zero crossings among the audited trusted leakage groups and a 151.7 largest-to-smallest class ratio. A fully fine-tuned DINOv3 ConvNeXt-Tiny reference achieved 98.51% accuracy and 96.87% macro-F1 on the locked internal test. A compact MobileNetV4 Conv-Medium derivative achieved 98.46% accuracy and 96.27% macro-F1 without being presented as evidence for a new distillation method. Validation-only post-training quantisation selected dynamic activations with per-channel weights, and the final 22.60 MiB ExecuTorch/XNNPACK PTE achieved 98.46% accuracy and 96.23% macro-F1 when executed directly. Only six of 16,363 top-1 decisions changed between the converted INT8 graph and the PTE, while paired analysis showed a modest class-balanced loss; an exploratory post hoc fruit-label slice localized a larger recall decline than aggregate accuracy revealed. CropCop establishes strong leakage-controlled internal recognition and software-runtime fidelity; it does not establish performance on unseen farms, camera pipelines, or physical Android hardware.
Comments25 pages, 6 figures, and 15 tables. Includes benchmark-audit, model-retention, runtime-fidelity, and reproducibility appendices
