Foundation-model pipelines for individual-level livestock monitoring -- combining open-vocabulary detection, promptable video segmentation, and self-supervised visual embeddings -- have raised the accuracy ceiling of precision livestock farming (PLF), but their GPU memory budgets exceed the envelope of commodity edge accelerators. To close this gap, the 446M-parameter Perception Encoder (PE-ViT-L+) backbone of SAM 3 is distilled into a 40.66M-parameter multi-scale student through three mechanisms: a Feature Pyramid Network student encoder built on TinyViT-21M-512, a four-term direction-then-scale distillation loss, and backbone-substitution inference with sliding-window session pruning that bounds streaming GPU memory growth. The DINOv3 family includes a pre-distilled ViT-S/16 variant (21.6M parameters) released alongside a 6716M-parameter ViT-7B teacher; the ViT-S (21M) variant is adopted as the per-individual embedder. On the Edinburgh Pig dataset, the compressed pipeline reaches 92.29% MOTA and 96.15% IDF1 against the SAM 3 teacher (1.68- and 0.84-percentage-point losses), achieves a 7.77-fold reduction in system-level parameters and a 3.01-fold reduction in peak VRAM (19.52GB -> 6.49GB), and reaches 97.34% top-1 accuracy with 91.67% macro-F1 on nine-class pig behaviour classification. The pipeline fits inside an NVIDIA Jetson Orin NX 16GB envelope with 4.9GB of headroom, supporting a proposed -- but not yet empirically validated -- on-device embedding-pool re-identification mechanism whose per-individual footprint of approximately 94MB per animal per year produces a longitudinal visual record amenable to retrospective association with disease, lameness, reproductive, and growth outcome labels.

翻译：基于基础模型流水线的个体级牲畜监测——融合开放词汇检测、可提示视频分割与自监督视觉嵌入——已提升了精准畜牧业（PLF）的精度上限，但其GPU内存需求超出商用边缘加速器的承载范围。为弥合这一差距，本文将SAM 3中参数规模达4.46亿的感知编码器（PE-ViT-L+）主干网络，通过三种机制蒸馏至参数规模为4066万的多尺度学生网络：基于TinyViT-21M-512构建的特征金字塔网络学生编码器、四项方向-尺度级联蒸馏损失函数，以及基于滑动窗口会话剪枝的主干替换推理方法（可约束流式GPU内存增长）。DINOv3系列包含预蒸馏变体ViT-S/16（参数2160万）及同步发布的6716M参数ViT-7B教师模型，本文采用其中参数规模2100万的ViT-S变体作为个体级嵌入器。在爱丁堡猪数据集上，压缩流水线相较SAM 3教师模型实现92.29%的MOTA与96.15%的IDF1（分别损失1.68与0.84个百分点），系统级参数规模缩减7.77倍，峰值显存从19.52GB降至6.49GB（缩减3.01倍），并在九类猪行为分类任务中达到97.34%的top-1准确率与91.67%的宏F1分数。该流水线适配于显存容量16GB的NVIDIA Jetson Orin NX边缘平台，保留4.9GB余量，支持所提出的（尚未经实验验证的）设备端嵌入池重识别机制——该机制以每头牲畜每年约94MB的个体级存储开销，生成可回溯式关联疾病、跛行、繁殖及生长结局标签的时序视觉记录。