论文标题
范围头在对象检测中准确定位
Scope Head for Accurate Localization in Object Detection
论文作者
论文摘要
多阶段或单阶段管道中的现有基于锚和锚的对象探测器已达到非常有前途的检测性能。但是，他们仍然遇到手工制作的2D锚定义的设计难度以及1D直接位置回归中的学习复杂性。为了解决这些问题，在本文中，我们提出了一个新颖的探测器作为scopenet，该探测器将每个位置的锚定为相互依赖的关系。这种方法量化了预测空间，并采用粗到精细的策略来定位。与基于回归的无锚方法一样，它具有卓越的灵活性，而产生更精确的预测。此外，学会了继承锚定评分来指示检测结果的本地化质量，我们建议通过组合类别分类得分和锚定选择分数来更好地表示检测框的置信度。凭借我们简洁有效的设计，拟议的Scopenet在可可方面取得了最新的结果
Existing anchor-based and anchor-free object detectors in multi-stage or one-stage pipelines have achieved very promising detection performance. However, they still encounter the design difficulty in hand-crafted 2D anchor definition and the learning complexity in 1D direct location regression. To tackle these issues, in this paper, we propose a novel detector coined as ScopeNet, which models anchors of each location as a mutually dependent relationship. This approach quantizes the prediction space and employs a coarse-to-fine strategy for localization. It achieves superior flexibility as in the regression based anchor-free methods, while produces more precise prediction. Besides, an inherit anchor selection score is learned to indicate the localization quality of the detection result, and we propose to better represent the confidence of a detection box by combining the category-classification score and the anchor-selection score. With our concise and effective design, the proposed ScopeNet achieves state-of-the-art results on COCO
