[论文解读] Efficient Brood Cell Detection in Layer Trap Nests for Bees and Wasps: Balancing Labeling Effort and Species Coverage

Chenchang Liu, Felix Fornoff+4 more|OpenAgrar|Mar 17, 2026

Insect and Arachnid Ecology and Behavior被引用 0

一句话总结

本论文提出一种用于检测和分类层捕虫瓶巢（LTNs）中的 brood cells 的深度学习方法（YOLOv8），并引入约束型误报损失（CFPL）来处理未标注数据，在减少标注工作量的同时提升对常见与罕见物种的检测性能。

ABSTRACT

Monitoring cavity-nesting wild bees and wasps is vital for biodiversity research and conservation. Layer trap nests (LTNs) are emerging as a valuable tool to study the abundance and species richness of these insects, offering insights into their nesting activities and ecological needs. However, manually evaluating LTNs to detect and classify brood cells is labor-intensive and time-consuming. To address this, we propose a deep learning based approach for efficient brood cell detection and classification in LTNs. LTNs present additional challenges due to densely packed brood cells, leading to a high labeling effort per image. Moreover, we observe a significant imbalance in class distribution, with common species having notably more occurrences than rare species. Comprehensive labeling of common species is time-consuming and exacerbates data imbalance, while partial labeling introduces data incompleteness which degrades model performance. To reduce labeling effort and mitigate the impact of unlabeled data, we introduce a novel Constrained False Positive Loss (CFPL) strategy. CFPL dynamically masks predictions from unlabeled data, preventing them from interfering with the classification loss during training. We evaluate our approach on a dataset of 712 LTN images collected over one season, covering 28 fine-grained classes describing the taxonomy and status of brood cells. To minimize labeling effort, we limit the training set to a maximum of 300 labels per class. Experimental results demonstrate that deep learning can be effectively used to detect brood cells in LTNs. Our CFPL method further improves performance and balances model accuracy and labeling effort while also mitigating class imbalance.

研究动机与目标

• 动机：自动化监测空腔筑蜂和黄蜂，利用 LTNs 评估丰富度和物种丰富度。
• 问题：在不平衡的生态数据中，常见物种占比过高，全面标注所有实例在实践中不可行。
• 目标：开发并评估一种学习策略（CFPL），在训练中缓解未标注数据的影响。
• 实现：在真实的 LTN 图像数据集上，展示可行性并量化性能提升，标注有限样本。

提出的方法

• 将 YOLOv8 作为 LTNs 中 brood cells 的检测骨干。
• 引入约束型误报损失（CFPL），在分类损失计算时对未标注区域的预测进行掩蔽。
• 为每个类别标注最多 300 个样本，以在标注努力与数据完整性之间取得平衡。
• 将数据分为训练集（包含部分标注）、测试集和验证集；使用 712 张 LTN 图像，涵盖 28 个类别。
• 在多数类与少数类组之间比较基线 YOLOv8 与 CFPL 增强的 YOLOv8。

实验结果

研究问题

• RQ1 深度学习在有限标注数据条件下是否能在 LTNs 中检测 brood cells？
• RQ2 在存在未标注多数类样本的情况下，CFPL 是否提升检测性能？
• RQ3 CFPL 方法对多数类与少数类的精确度（AP）与召回率（Recall）有何影响？
• RQ4 在生态监测中采用部分标注策略时，实际的标注工作量节省是多少？

主要发现

• YOLOv8 基线在多数类的 AP 为 63.11%、召回率为 7.05%；CFPL 提升至多数类 AP 66.11%、召回率 46.54%。
• 对于少数类，AP 从 44.29% 提升至 45.83%，召回率从 31.46% 提升至 35.57%（CFPL）。
• CFPL 减少未标注的多数类样本被误判为背景的情况，背景误分类平均从 0.56 降至 0.33。
• 总体而言，CFPL 为多数类带来显著的召回提升（约 39.49 个百分点），对两组均带来适度的 AP 增益，显示标注工作量与性能之间的更优权衡。
• 该数据集与 CFPL 在每个类别标注少于 300 个样本时即可实现有效检测，凸显在生态监测中的实际适用性。