哦，鹿啊，我该如何应对？用于选择性野生动物标注与分类的季节先验
Oh Deer, How Should I Handle This? Seasonal Priors for Selective Wildlife Annotation and Classification
查看机构详情
- Aalborg University（奥尔堡大学）
- University of Applied Sciences Upper Austria（上奥地利应用科学大学）
- Massachusetts Institute of Technology（麻省理工学院）
机构由 AI 辅助整理，请以论文原文为准。
浏览论文内容
中文总结 AI 辅助
该研究针对航拍野生动物分类的标签不可靠问题，以马鹿雄性识别为对象，利用季节先验结合多模态数据提升标注与分类效果，提出的方法可指导标注协议设计和模态加权。
中文摘要 AI 辅助
航拍图像中的细粒度野生动物分类不仅受限于模型性能，还受限于不可靠的标签：动物仅占据少量像素，关键视觉线索随季节变化，且特定模态的证据可能存在歧义。我们研究了马鹿的成年雄性识别，其中鹿茸周期定义了标注和预测的可靠证据的可预测窗口。使用由三名标注者标注的7295组仅RGB、仅热成像以及匹配的RGB+热成像裁剪数据集，我们表明季节结构将（I）标注质量、（II）下游分类和（III）选择性预测关联起来。匹配的RGB+热成像审查比任一单一模态能解决更多样本，恢复了原本仅RGB或仅热成像会遗漏的多数雄性标签，无论是基于人类还是基于模型的分类均如此。标注者弃权（不执行）率高的月份，分类器置信度也更低，而软季节先验主要有益于受季节限制的热成像视图。不确定性带弃权（不执行）进一步将覆盖准确率提升至98.9%，尽管覆盖范围有所减少，且推迟判断的情况不成比例地落在雄性身上。总体而言，基于生物学的季节日历可预测标注和预测不可靠的场景，能指导标注协议设计和模态加权。
英文摘要
Fine-grained wildlife classification in aerial imagery is limited not only by model performance, but also by unreliable labels: animals occupy few pixels, key visual cues vary seasonally, and modality-specific evidence can be ambiguous. We study adult-male identification in red deer ($\textit{Cervus elaphus}$), where the antler cycle defines predictable windows of reliable evidence for both annotation and prediction. Using 7,295 RGB-only, thermal-only, and matched RGB+thermal crop sets from low-altitude UAV surveys, labeled by three annotators, we show that seasonal structure links (I) annotation quality, (II) downstream classification, and (III) selective prediction. Matched RGB+thermal review resolves more samples than either single modality, recovering majority-male labels otherwise missed by RGB or thermal alone, in human-based as well as model-based classification. Months with high annotator abstention also show lower classifier confidence, and soft seasonal priors mainly benefit the season-limited thermal view. Uncertainty-band abstention further raises covered accuracy to 98.9%, though at reduced coverage and with deferral that falls disproportionately on males. Overall, a biologically grounded seasonal calendar predicts where annotation and prediction are unreliable, and can guide both annotation protocol design and modality weighting.
