论文标题
重新点V2：验证符合对象检测的回归
RepPoints V2: Verification Meets Regression for Object Detection
论文作者
论文摘要
验证和回归是神经网络预测的两种通用方法。每个都有自己的优势：验证可以更易于准确地推断，并且回归更有效，并且适用于连续目标变量。因此，仔细结合它们以利用其利益通常是有益的。在本文中，我们采用这种理念来改善最新的对象检测，特别是通过重置。尽管重新点提供了高性能，但我们发现它对物体本地化的回归的巨大依赖为改进留出了空间。我们将验证任务介绍到重置的本地化预测中，并产生重置V2，该v2通过使用不同的骨干和训练方法对可可对象检测基准测试的原始重点进行了大约2.0映射的一致改进。 Reppoints V2还通过单个模型在Coco \ texttt {test-dev}上实现了52.1映射。此外，我们表明所提出的方法通常可以提升其他对象检测框架以及实例分割等应用程序。该代码可在https://github.com/scalsol/reppointsv2上找到。
Verification and regression are two general methodologies for prediction in neural networks. Each has its own strengths: verification can be easier to infer accurately, and regression is more efficient and applicable to continuous target variables. Hence, it is often beneficial to carefully combine them to take advantage of their benefits. In this paper, we take this philosophy to improve state-of-the-art object detection, specifically by RepPoints. Though RepPoints provides high performance, we find that its heavy reliance on regression for object localization leaves room for improvement. We introduce verification tasks into the localization prediction of RepPoints, producing RepPoints v2, which provides consistent improvements of about 2.0 mAP over the original RepPoints on the COCO object detection benchmark using different backbones and training methods. RepPoints v2 also achieves 52.1 mAP on COCO \texttt{test-dev} by a single model. Moreover, we show that the proposed approach can more generally elevate other object detection frameworks as well as applications such as instance segmentation. The code is available at https://github.com/Scalsol/RepPointsV2.
