论文标题
双重加权标签分配方案用于对象检测
A Dual Weighting Label Assignment Scheme for Object Detection
论文作者
论文摘要
标签分配（LA）旨在将每个训练样本分配为正（POS）和负（负（负）负重）在对象检测中起重要作用。现有的LA方法主要集中在POS加权函数的设计上，而负重的重量直接源自POS权重。这种机制限制了检测器的学习能力。在本文中，我们探索了一种新的加权范式，称为双重加权（DW），以分别指定POS和负重。我们首先通过分析对象检测中的评估指标，然后设计基于它们的POS和负权重功能，从而确定POS/NEG权重的关键影响因素。具体而言，样品的POS权重由其分类和定位分数之间的一致性确定，而负重分解为两个术语：它是neg样本且重要性的概率，其重要性是作为负样本。这样的加权策略提供了更大的灵活性，可以区分重要和不太重要的样本，从而产生更有效的对象检测器。配备了建议的DW方法，单个FCOS-Resnet-50检测器可以在1倍时间表下可可的可可达到41.5％的地图，表现优于其他现有的LA方法。它始终通过在没有铃铛和哨子的各种骨架下的大幅度来改善可可的基准。代码可在https://github.com/strongwolf/dw上找到。
Label assignment (LA), which aims to assign each training sample a positive (pos) and a negative (neg) loss weight, plays an important role in object detection. Existing LA methods mostly focus on the design of pos weighting function, while the neg weight is directly derived from the pos weight. Such a mechanism limits the learning capacity of detectors. In this paper, we explore a new weighting paradigm, termed dual weighting (DW), to specify pos and neg weights separately. We first identify the key influential factors of pos/neg weights by analyzing the evaluation metrics in object detection, and then design the pos and neg weighting functions based on them. Specifically, the pos weight of a sample is determined by the consistency degree between its classification and localization scores, while the neg weight is decomposed into two terms: the probability that it is a neg sample and its importance conditioned on being a neg sample. Such a weighting strategy offers greater flexibility to distinguish between important and less important samples, resulting in a more effective object detector. Equipped with the proposed DW method, a single FCOS-ResNet-50 detector can reach 41.5% mAP on COCO under 1x schedule, outperforming other existing LA methods. It consistently improves the baselines on COCO by a large margin under various backbones without bells and whistles. Code is available at https://github.com/strongwolf/DW.
