CascadeCropNet：基于安全级联推理的农作物损伤评估——肯尼亚小农户玉米保险图像应用（arXiv:2607.25468，2026-07-28提交，预印本）
提出CascadeCropNet级联架构，针对小农户玉米保险图像损伤评估，显著降低漏检率，方法新颖且数据规模大，对农业保险精准理赔有重要参考价值。
Hagbe JTM、Gounou GK 与 Zimé SK 在 arXiv 提交预印本"Safety-Aware Cascaded Inference for Crop Damage Assessment with Controlled Error Trade-offs"（arXiv:2607.25468 [cs.CV]，2026-07-28提交）。针对基于图像的农业保险中漏检成本远高于误报的非对称代价结构，提出 CascadeCropNet 两阶段级联架构：通过阈值选择满足目标召回约束（Rec-Damaged ≥ 0.95），轻量 Sentinel 模型先做二分类健康分诊，超过损伤概率阈值 τ 的样本升级到专家 Expert 模型做精细诊断。在 Eyes on the Ground 数据集（肯尼亚小农户玉米田 23,804 张图像）上，τ=0.5 时 Rec-Damaged 达 0.974，相对单模型基线漏检减少最多54%。注：该方法可靠性取决于阈值与部署条件，并非任意分布漂移下的绝对保证。
Abstract:In picture-based agricultural insurance for smallholder farmers, missed damage detections carry substantially higher cost than false alarms: a farmer who sustained real losses receives no payout, while unnecessary expert review is operationally costly but reversible. Standard multi-class classifiers optimize global accuracy but provide no mechanism to operationalize or control this asymmetric cost structure at inference time. We propose CascadeCropNet, a two-stage cascade architecture calibrated to satisfy a target recall constraint (Rec-Damaged >= 0.95) through threshold selection. A lightweight Sentinel model performs binary health triage; samples exceeding a calibrated damage probability threshold tau are escalated to a specialist Expert model for fine-grained diagnosis. This design provides explicit, deployment-time control over the safety-efficiency trade-off without retraining. Evaluated on the Eyes on the Ground dataset (23,804 images from Kenyan smallholder maize farms), the cascade achieves Rec-Damaged = 0.974 at tau = 0.5, reducing missed damage cases by up to 54% relative to a flat baseline. Under evaluation alignment, the representational gap reduces to +0.008 F1-macro, confirming the contribution is architectural rather than representational. Under input degradation, the system prioritizes escalation over confident misclassification, reflecting error containment through architectural isolation rather than intrinsic model robustness. These results demonstrate that cascade architectures can operationalize safety-oriented decision constraints through calibrated routing in settings where reliability matters more than aggregate accuracy. These properties depend on threshold calibration and deployment conditions and do not constitute guarantees under arbitrary distribution shift.
Comments:44 pages, 7 figures, 12 tables. Submitted to Precision Agriculture, July 2026
Subjects:Computer Vision and Pattern Recognition (cs.CV)
Cite as:arXiv:2607.25468 [cs.CV]
(or arXiv:2607.25468v1 [cs.CV] for this version)
https://doi.org/10.48550/arXiv.2607.25468
arXiv-issued DOI via DataCite (pending registration)
Submission history
From: Jose Thiery Messigbede Hagbe [view email]
[v1] Tue, 28 Jul 2026 09:01:27 UTC (507 KB)