适应中心和尺度预测：更加稳定和准确
Adapted Center and Scale Prediction: More Stable and More Accurate
AI总结：
本文提出了一种基于中心和尺度预测（CSP）的改进方法，旨在结合无锚点检测器的简洁性和两阶段检测器的准确性，通过增强CSP的鲁棒性、提出压缩宽度的新方法，并在CityPersons基准上取得第二名的性能，同时探索了可切换归一化的能力。
摘要：
行人检测受益于深度学习技术，在近年来迅速发展。大多数检测器遵循通用目标检测框架，即默认框和两阶段过程。最近，无锚点和单阶段检测器被引入到这一领域。然而，它们的准确性并不令人满意。因此，为了同时享受无锚点检测器的简洁性和两阶段检测器的准确性，我们基于检测器提出了一些改进，即中心和尺度预测（CSP）。本文的主要贡献包括：（1）我们改进了CSP的鲁棒性，使其更容易训练。（2）我们提出了一种新的方法来预测宽度，即压缩宽度。（3）我们在CityPersons基准上取得了第二好的性能，即在合理集上9.3%的log-average miss rate（MR），在部分集上8.7%的MR，在裸集上5.6%的MR，这表明无锚点和单阶段检测器仍能保持高精度。（4）我们探索了可切换归一化的一些能力，这些能力在原始论文中未被提及。代码可在https://github.com/WangWenhao0716/Adapted-Center-and-Scale-Prediction上公开获取。
英文摘要：
Pedestrian detection benefits from deep learning technology and gains rapid development in recent years. Most of detectors follow general object detection frame, i.e. default boxes and two-stage process. Recently, anchor-free and one-stage detectors have been introduced into this area. However, their accuracies are unsatisfactory. Therefore, in order to enjoy the simplicity of anchor-free detectors and the accuracy of two-stage ones simultaneously, we propose some adaptations based on a detector, Center and Scale Prediction(CSP). The main contributions of our paper are: (1) We improve the robustness of CSP and make it easier to train. (2) We propose a novel method to predict width, namely compressing width. (3) We achieve the second best performance on CityPersons benchmark, i.e. 9.3% log-average miss rate(MR) on reasonable set, 8.7% MR on partial set and 5.6% MR on bare set, which shows an anchor-free and one-stage detector can still have high accuracy. (4) We explore some capabilities of Switchable Normalization which are not mentioned in its original paper. The code is publicly available at https://github.com/WangWenhao0716/Adapted-Center-and-Scale-Prediction.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
