[论文] BoviShift: A Six-Year Multi-Attribute Audit of Visual Cattle Phenotypi...

论文概要

研究领域: CV 作者: Mobasshir Bhuiya Shagor, Nilambar Halder Tonmoy, Md Saef Ullah Miah 发布时间: 2026-11-10 arXiv: 2611.14476

中文摘要

计算机视觉为估算牲畜性状提供了可扩展的非接触手段，但相关图像与视频帧使可靠评估困难。图像随机划分可能把同一动物的不同视角同时放进训练集与测试集，实际部署还需迁移到未来年份采集的动物。我们提出 BoviShift：从 2021 到 2026 年运营中牛只市场六个连续年度队列重建的语料库，含 2657 头牛、10610 张静态图像与 2566 段环绕行走视频，覆盖九个已记录的牛品种类别。我们通过四种配置评估三种划分策略：同一开发队列上的图像随机与合并牛只不相交划分，加上单独的未来 2025 与锁定未来 2026 评估。使用固定 ResNet-50 多任务基线，评估体重、年龄、身高、品种与毛色。图像随机与牛只不相交划分的差异是任务依赖的，而非普遍的泄漏惩罚。未来队列行为也是属性与队列特异的：品种相对合并评估下降；平均体重与年龄在 2025 年未超常数基线；身高保持基线之上；毛色 2025 年迁移良好但 2026 年退化。多任务训练在单种子消融中改进全部五个点估计；静态视角聚合有选择地有帮助；零样本视频帧聚合暴露出静态到视频的域差距。据我们所知，BoviShift 是跨度最长、结合连续年度队列与生理和视觉属性的牛只视觉资源。

原文摘要

Computer vision offers a scalable, non-contact means of estimating livestock traits, but correlated images and video frames make reliable evaluation difficult. Image-random splitting can place views of the same animal in both training and test sets, while deployment further requires transfer to animals captured in future years. We introduce BoviShift, a corpus reconstructed from six consecutive annual cohorts of an operational cattle marketplace collected from 2021 to 2026. It contains 2{,}657 cattle, 10{,}610 still images, and 2{,}566 walk-around videos across nine recorded breed categories. We evaluate three splitting strategies through four configurations: image-random and pooled cattle-disjoint splits over the same development cohorts, followed by separate future-2025 and locked future...

#论文 #arXiv #CV #小凯