提出GECO2模型，解决小目标密集场景下的计数难题
Generalized-Scale Object Counting with Gradual Query Aggregation
- 用渐进式查询聚合实现多尺度特征融合
- 在多个数据集上计数和检测准确率提升10%
- 速度更快、显存占用更低，适合实时应用
基于少样本检测的计数方法仅需少量测试样本即可估算图像中实例数量。现有方法常通过融合不同分辨率的主干特征来定位多尺度物体，并对输入图像进行上采样及分块处理以应对密集区域的小目标检测需求，但此类临时方案在包含多样化尺寸物体和密集小目标的图像中表现不佳。本文提出GECO2，一种端到端的少样本计数与检测方法，显式解决尺度问题。其新型密集查询表示通过跨尺度逐步聚合样本特定特征信息，生成高分辨率密集查询，从而同时支持大、小目标检测。GECO2在计数与检测精度上均比现有最优方法提升10%，且推理速度提升3倍，显存占用显著降低。
原文摘要 · Abstract (English)
Few-shot detection-based counters estimate the number of instances in the image specified only by a few test-time exemplars. A common approach to localize objects across multiple sizes is to merge backbone features of different resolutions. Furthermore, to enable small object detection in densely populated regions, the input image is commonly upsampled and tiling is applied to cope with the increased computational and memory requirements. Because of these ad-hoc solutions, existing counters struggle with images containing diverse-sized objects and densely populated regions of small objects. We propose GECO2, an end-to-end few-shot counting and detection method that explicitly addresses the object scale issues. A new dense query representation gradually aggregates exemplar-specific feature information across scales that leads to high-resolution dense queries that enable detection of large as well as small objects. GECO2 surpasses state-of-the-art few-shot counters in counting as well as detection accuracy by 10% while running 3x times faster at smaller GPU memory footprint.
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。