Search papers, labs, and topics across Lattice.
CropCop is a robust plant-health recognition system that categorizes 120 classes, built on a meticulously audited dataset of 117,546 images, which underwent rigorous duplicate verification to ensure data integrity. The model achieved impressive accuracy rates of 98.51% and 98.46% using DINOv3 and MobileNetV4 architectures, respectively, while maintaining a compact runtime artifact of only 22.60 MiB. Notably, the approach emphasizes leakage control and software-runtime fidelity, although it does not assess performance in real-world agricultural settings.
Achieving over 98% accuracy with a compact model, CropCop sets a new standard for plant-health recognition while ensuring data integrity through rigorous auditing.
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.
