论文标题
重新访问对象检测器中的兄弟姐妹
Revisiting the Sibling Head in Object Detector
论文作者
论文摘要
首先以快速的rcnn〜 \ cite {girshick2015fast}表示``分类和本地化的共享头''（同级头）在过去五年中一直领先对象检测社区的时尚。本文提供了这样的观察，即同胞头部两个对象函数之间的空间错位可能会极大地损害训练过程，但是这种未对准可以通过一个非常简单的操作员来解决，称为任务感知的空间分解（TSD）。考虑到分类和回归，TSD通过为它们生成两个分离的建议，使它们与空间维度相脱离，这是由共享建议估算的。这是受自然见解的启发，即在一个实例中，某些显着区域中的特征可能具有丰富的信息进行分类，而边界周围的这些特征在边界框回归中可能良好。令人惊讶的是，这种简单的设计可以在MS Coco和Google OpenImage上提高所有骨干和型号，并始终提高〜3％的地图。此外，我们提出了一个渐进式约束，以扩大分解和共享建议之间的性能范围，并增加了约1％的地图。我们显示了\ algname {}通过较大的边距突破了当今的单模检测器的上限（MAP 49.4与resnet-101，51.2一起使用Senet154），并且是Google OpenImage挑战2019年第一个位置解决方案的核心模型。
The ``shared head for classification and localization'' (sibling head), firstly denominated in Fast RCNN~\cite{girshick2015fast}, has been leading the fashion of the object detection community in the past five years. This paper provides the observation that the spatial misalignment between the two object functions in the sibling head can considerably hurt the training process, but this misalignment can be resolved by a very simple operator called task-aware spatial disentanglement (TSD). Considering the classification and regression, TSD decouples them from the spatial dimension by generating two disentangled proposals for them, which are estimated by the shared proposal. This is inspired by the natural insight that for one instance, the features in some salient area may have rich information for classification while these around the boundary may be good at bounding box regression. Surprisingly, this simple design can boost all backbones and models on both MS COCO and Google OpenImage consistently by ~3% mAP. Further, we propose a progressive constraint to enlarge the performance margin between the disentangled and the shared proposals, and gain ~1% more mAP. We show the \algname{} breaks through the upper bound of nowadays single-model detector by a large margin (mAP 49.4 with ResNet-101, 51.2 with SENet154), and is the core model of our 1st place solution on the Google OpenImage Challenge 2019.
