Advances in artificial intelligence for computer vision hold great promise for increasing the scales at which ecological systems can be studied. The distribution and behavior of individuals is central to ecology, and computer vision using deep neural networks can learn to detect individual objects in imagery. However, developing supervised models for ecological monitoring is challenging because it requires large amounts of human-labeled training data, requires advanced technical expertise and computational infrastructure, and is prone to overfitting. This limits application across space and time. One solution is developing generalized models that can be applied across species and ecosystems. Using over 250,000 annotations from 13 projects from around the world, we develop a general bird detection model that achieves over 65% recall and 50% precision on novel aerial data without any local training despite differences in species, habitat, and imaging methodology. Fine-tuning this model with only 1000 local annotations increases these values to an average of 84% recall and 69% precision by building on the general features learned from other data sources. Retraining from the general model improves local predictions even when moderately large annotation sets are available and makes model training faster and more stable. Our results demonstrate that general models for detecting broad classes of organisms using airborne imagery are achievable. These models can reduce the effort, expertise, and computational resources necessary for automating the detection of individual organisms across large scales, helping to transform the scale of data collection in ecology and the questions that can be addressed.

中文翻译：

---

高分辨率机载图像鸟类检测的通用深度学习模型

计算机视觉人工智能的进步为扩大生态系统的研究规模带来了巨大希望。个体的分布和行为是生态学的核心，使用深度神经网络的计算机视觉可以学习检测图像中的个体对象。然而，开发用于生态监测的监督模型具有挑战性，因为它需要大量人工标记的训练数据，需要先进的技术专长和计算基础设施，并且容易过度拟合。这限制了跨空间和时间的应用。一种解决方案是开发可跨物种和生态系统应用的通用模型。使用来自世界各地 13 个项目的超过 250,000 个注释，我们开发了一种通用的鸟类检测模型，尽管物种、栖息地和成像方法存在差异，但无需任何本地训练即可在新的航空数据上实现超过 65% 的召回率和 50% 的精度。通过建立从其他数据源学习的一般特征，使用仅 1000 个局部注释对该模型进行微调，将这些值提高到平均 84% 的召回率和 69% 的准确率。即使在中等规模的注释集可用时，从通用模型进行再训练也能改善局部预测，并使模型训练更快、更稳定。我们的结果表明，使用机载图像检测广泛类别生物体的通用模型是可以实现的。这些模型可以减少在大范围内自动检测个体生物所需的工作量、专业知识和计算资源，