Backdoor-Trigger Evaluation for Computer Agriculture Disease-Detection Models Under Third-Party Pretrained Checkpoints: An Artificial Intelligence Poisoning-Rate Audit
将后门触发器视为预训练检查点供应链属性，量化微调后后门存活的投毒率。
← 主题
作物病害检测 农业人工智能
同时包含 作物病害检测、农业人工智能 的农业资讯，共 3 条。
MMTA-ACDD: Multi-teacher online adaptive learning and multimodal augmentation synergy for robust crop disease detection
提出多教师在线自适应与多模态增强框架，提升作物病害实时检测模型在动态环境下的鲁棒性。
Lightweight architecture optimization of YOLOv12n for improved cotton verticillium wilt detection
提出轻量模型YOLO-SCOD，实现棉花黄萎病精准检测。