AutoAssign: Differentiable Label Assignment for Dense Object Detection
Benjin Zhu Jianfeng Wang Zhengkai Jiang Fuhang Zong Songtao Liu Zeming Li Jian Sun MEGVII Technology {zhubenjin, wangjianfeng, jiangzhengkai, zongfuhang, liusongtao, lizeming,
Abstract
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.
中文速览
目标检测中每个候选位置该被标为正样本还是负样本，这一"标签分配"问题长期依赖人工设计的规则（如锚框、IoU阈值、固定中心区域），难以适应外观差异巨大的不同类别和实例。AutoAssign提出了一套全可微的加权机制，用"类别中心加权"学习每个类别特有的空间分布先验，用"置信度加权"根据每个实例的分类与定位置信度动态决定哪些位置应作为正/负样本，两者联合生成权重图，将空间和尺度维度的标签分配统一在一个端到端可训练的框架中。在MS COCO上，AutoAssign在多种骨干网络下均大幅超越现有最优采样策略，最佳模型达到52.1% AP，超过所有已有单阶段检测器；在PASCAL VOC、Objects365和WiderFace上的结果也验证了其广泛适用性。这项工作的意义在于，它从根本上把标签分配从"人工规则驱动"转变为"数据和外观驱动"，为检测器提供了一条摆脱繁琐超参调优的新路径。
原文 arXiv:2007.03496;中英对照 + 大白话阅读 https://aha.fim.ai/paper/2007.03496v3