将大模型压缩到边缘设备，实现猪只个体级长期视觉监控。
Lightweight Distillation of SAM 3 and DINOv3 for Edge-Deployable Individual-Level Livestock Monitoring and Longitudinal Visual Analytics
- 用三机制压缩SAM3和DINOv3大模型，降低参数与显存占用。
- 在猪只行为识别上达97.34%准确率，显存降至6.49GB。
- 适合部署在Jetson边缘设备，支持长期个体追踪分析。
面向个体级畜禽监测的基座模型流程——结合开放词汇检测、可提示视频分割和自监督视觉嵌入——显著提升了精准畜牧养殖的精度上限，但其GPU内存需求超出主流边缘加速器承载范围。为弥合这一差距，将SAM3中446M参数的感知编码器（PE-ViT-L+）通过三种机制压缩为40.66M参数的多尺度学生模型：基于TinyViT-21M-512构建的特征金字塔网络学生编码器、四元组方向-尺度蒸馏损失，以及滑动窗口会话剪枝的主干替换推理策略，有效控制流式处理中的显存增长。DINOv3家族包含预蒸馏的ViT-S/16（21.6M参数）与6716M参数的ViT-7B教师模型；本文采用21M参数的ViT-S作为个体嵌入器。在爱丁堡猪数据集上，压缩后系统达到92.29% MOTA与96.15% IDF1，较原SAM3教师模型分别下降1.68和0.84个百分点；系统参数量减少7.77倍，峰值显存从19.52GB降至6.49GB；在九类猪行为分类任务中，实现97.34%的顶1准确率与91.67%宏平均F1。该方案可部署于配备16GB内存的NVIDIA Jetson Orin NX，剩余4.9GB空间，支持一种尚未实证验证的本地化嵌入池重识别机制，每头猪每年个体足迹约94MB，生成可追溯疾病、跛行、繁殖及生长表现的纵向视觉记录。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。