论文标题
自动分配：密集对象检测的可区分标签分配
AutoAssign: Differentiable Label Assignment for Dense Object Detection
论文作者
论文摘要
确定对象检测的正/负样本称为标签分配。在这里，我们提出了一个名为AutoSign的无锚探测器。它几乎不需要人类的知识，并通过完全可区分的加权机制实现了外观。在培训期间，为了满足数据的先前分布和适应类别特征，我们提出中心加权以调整特定类别的先前分布。为了适应对象外观，提出了置信度加权以调整每个实例的特定分配策略。然后将两个加权模块组合在一起以产生正权重，以调整每个位置的置信度。在MS Coco上进行的广泛实验表明，我们的方法通过具有各种骨架的大边缘稳定地超过了其他最佳抽样策略。此外，我们的最佳模型可实现52.1％的AP，表现优于所有现有的一阶段探测器。此外，在其他数据集上进行的实验，例如Pascal VOC，Objects365和Flideface，展示了自动分配的广泛适用性。
Determining positive/negative samples for object detection is known as label assignment. Here we present an anchor-free detector named AutoAssign. It requires little human knowledge and achieves appearance-aware through a fully differentiable weighting mechanism. During training, to both satisfy the prior distribution of data and adapt to category characteristics, we present Center Weighting to adjust the category-specific prior distributions. To adapt to object appearances, Confidence Weighting is proposed to adjust the specific assign strategy of each instance. The two weighting modules are then combined to generate positive and negative weights to adjust each location's confidence. Extensive experiments on the MS COCO show that our method steadily surpasses other best sampling strategies by large margins with various backbones. Moreover, our best model achieves 52.1% AP, outperforming all existing one-stage detectors. Besides, experiments on other datasets, e.g., PASCAL VOC, Objects365, and WiderFace, demonstrate the broad applicability of AutoAssign.
