用单头协同注意力模型精准检测极小的蜂类，解决标注偏倚问题。
Where Is the Bee? Detecting Tiny Pollinators with a Single Collaborative-Head Transformer
- 采用协同头Transformer架构，结合Swin-L骨干网络提升小目标检测能力。
- 通过作物拼接数据增强与类权重ETF损失函数，使稀有类占比从19.9%升至55.1%。
- 无需测试时增强，在1920x1080图像上达0.5062 mAP@[.5:.95]，排名第一。
CVPPA@ECCV 2026 BuzzSpot挑战要求在1920x1080田间关键帧中检测蜜蜂、大黄蜂、食蚜蝇和蛾类。其标注具有双重难点：目标框中位面积仅占画面的0.16%，且蜜蜂占标签总数的80%。为应对小目标，我们在预留关键帧上对比10种检测器配置，发现使用Swin-L主干的Co-DINO在mAP上表现最优，故选之。训练阶段通过两种方式缓解蜜蜂主导问题：一是在作物拼接数据池上微调，使三类稀有物种的总标注占比从19.9%提升至55.1%；二是引入类权重单纯形等角紧框架（ETF）损失，将匹配解码器查询的投影状态拉向固定类别方向。完整训练流程共12+3+2个周期。未使用推理时集成或测试时增强，最终在FinalTest上以0.5062 mAP@[.5:.95]排名第一。
原文摘要 · Abstract (English)
The CVPPA@ECCV 2026 BuzzSpot Challenge asks us to detect bees, bumblebees, hoverflies, and moths in 1920x1080 field keyframes. Its annotations carry 2 difficulties: the median box occupies 0.16% of a frame, and bees account for 80% of the labels. To cope with the small boxes, we compare 10 recorded detector configurations on held-out keyframes; plain Co-DINO with a Swin-L backbone has the highest mAP in this comparison, so we select it. Training then addresses the bee dominance in 2 ways: fine-tuning on a crop-mosaic pool in which the combined annotation share of the 3 rare classes rises from 19.9% to 55.1%, and a class-weighted simplex equiangular tight frame (ETF) loss that pulls the projected states of matched decoder queries toward fixed class directions. The full schedule spans 12+3+2 epochs. Without inference-time ensembling or test-time augmentation, we rank first on FinalTest at 0.5062 mAP@[.5:.95].
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。