新模型GeCo统一实现低样本目标检测分割与计数，精度显著提升。
A Novel Unified Architecture for Low-Shot Counting by Detection and Segmentation
- 用密集查询机制增强原型泛化能力，应对对象外观多样性。
- 提出直接优化检测任务的新计数损失，避免传统损失的缺陷。
- 在多个低样本计数场景下刷新最佳性能，适合高精度计数需求。
低样本目标计数器通过少量或无标注样例估计图像中物体数量。现有方法通过匹配原型进行物体定位，原型由无监督的全局图像外观聚合构建。由于物体外观差异大，易导致过度泛化和误检。且表现最优的方法使用代理损失训练定位，该损失在每个物体中心预测单位高斯分布，对标注误差、超参数敏感，且不直接优化检测任务，造成计数效果不佳。本文提出GeCo，一种统一架构的低样本计数模型，可同时实现准确的物体检测、分割与计数。GeCo通过新型密集物体查询设计，稳健地跨不同外观泛化原型；并引入新型计数损失，直接优化检测任务，避免标准代理损失的问题。GeCo在总计数平均绝对误差（MAE）上比领先方法提升约25%，检测精度更优，并在所有低样本计数设置中达到新的基准水平。
原文摘要 · Abstract (English)
Low-shot object counters estimate the number of objects in an image using few or no annotated exemplars. Objects are localized by matching them to prototypes, which are constructed by unsupervised image-wide object appearance aggregation. Due to potentially diverse object appearances, the existing approaches often lead to overgeneralization and false positive detections. Furthermore, the best-performing methods train object localization by a surrogate loss, that predicts a unit Gaussian at each object center. This loss is sensitive to annotation error, hyperparameters and does not directly optimize the detection task, leading to suboptimal counts. We introduce GeCo, a novel low-shot counter that achieves accurate object detection, segmentation, and count estimation in a unified architecture. GeCo robustly generalizes the prototypes across objects appearances through a novel dense object query formulation. In addition, a novel counting loss is proposed, that directly optimizes the detection task and avoids the issues of the standard surrogate loss. GeCo surpasses the leading few-shot detection-based counters by $\sim$25\% in the total count MAE, achieves superior detection accuracy and sets a new solid state-of-the-art result across all low-shot counting setups.
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。