论文标题
在拥挤的场景中进行性端到端对象检测
Progressive End-to-End Object Detection in Crowded Scenes
论文作者
论文摘要
在本文中，我们提出了一个新的基于查询的检测框架，用于人群检测。以前的基于查询的检测器具有两个缺点：首先，将针对一个对象推断出多个预测，通常在拥挤的场景中；其次，随着解码阶段的深度增加，性能会饱和。从一对一的标签分配规则的性质中受益，我们提出了一种渐进的预测方法来解决上述问题。具体而言，我们首先选择容易产生真正积极预测的可接受的查询，然后根据先前接受的预测来完善其余的嘈杂查询。实验表明，我们的方法可以显着提高拥挤场景中基于查询的检测器的性能。配备了我们的方法，稀疏的RCNN达到92.0 \％$ \ text {ap} $，41.4 \％$ \ text {mr}^{ - 2} $和83.2 \％$ \ text {ji {ji {ji} $ \ cite {chu2020 -detection}在处理拥挤的方案中指定。此外，所提出的方法，强大到拥挤，仍然可以对中等和略有拥挤的数据集进行一致的改进，例如Citypersons \ Cite {Zhang2017CityPersons}和Coco \ cite {lin2014microsoft}。代码将在https://github.com/megvii-model/iter-e2edet上公开提供。
In this paper, we propose a new query-based detection framework for crowd detection. Previous query-based detectors suffer from two drawbacks: first, multiple predictions will be inferred for a single object, typically in crowded scenes; second, the performance saturates as the depth of the decoding stage increases. Benefiting from the nature of the one-to-one label assignment rule, we propose a progressive predicting method to address the above issues. Specifically, we first select accepted queries prone to generate true positive predictions, then refine the rest noisy queries according to the previously accepted predictions. Experiments show that our method can significantly boost the performance of query-based detectors in crowded scenes. Equipped with our approach, Sparse RCNN achieves 92.0\% $\text{AP}$, 41.4\% $\text{MR}^{-2}$ and 83.2\% $\text{JI}$ on the challenging CrowdHuman \cite{shao2018crowdhuman} dataset, outperforming the box-based method MIP \cite{chu2020detection} that specifies in handling crowded scenarios. Moreover, the proposed method, robust to crowdedness, can still obtain consistent improvements on moderately and slightly crowded datasets like CityPersons \cite{zhang2017citypersons} and COCO \cite{lin2014microsoft}. Code will be made publicly available at https://github.com/megvii-model/Iter-E2EDET.
