Current state-of-the-art two-stage detectors heavily rely on region proposals to guide the accurate detection for objects. In previous region proposal approaches, the interaction between different functional modules is correlated weakly, which limits or decreases the performance of region proposal approaches. In this paper, we propose a novel two-stage strong correlation learning framework, abbreviated as SC-RPN, which aims to set up stronger relationship among different modules in the region proposal task. Firstly, we propose a Light-weight IoU-Mask branch to predict intersection-over-union (IoU) mask and refine region classification scores as well, it is used to prevent high-quality region proposals from being filtered. Furthermore, a sampling strategy named Size-Aware Dynamic Sampling (SADS) is proposed to ensure sampling consistency between different stages. In addition, point-based representation is exploited to generate region proposals with stronger fitting ability. Without bells and whistles, SC-RPN achieves AR1000 14.5% higher than that of Region Proposal Network (RPN), surpassing all the existing region proposal approaches. We also integrate SC-RPN into Fast R-CNN and Faster R-CNN to test its effectiveness on object detection task, the experimental results achieve a gain of 3.2% and 3.8% in terms of mAP compared to the original ones.

中文翻译：

---

用于电子医疗架构中完整步态分析的非侵入式可穿戴光学传感器


当前最先进的两级检测器严重依赖区域建议来指导物体的准确检测。在以前的区域提议方法中，不同功能模块之间的交互相关性较弱，这限制或降低了区域提议方法的性能。在本文中，我们提出了一种新颖的两阶段强相关学习框架，简称为SC-RPN，其目的是在区域提议任务中的不同模块之间建立更强的关系。首先，我们提出了一个轻量级 IoU-Mask 分支来预测交并（IoU）掩码并细化区域分类分数，它用于防止高质量区域提案被过滤。此外，提出了一种名为大小感知动态采样（SADS）的采样策略来确保不同阶段之间的采样一致性。此外，利用基于点的表示来生成具有更强拟合能力的区域建议。在没有花哨的情况下，SC-RPN 的 AR1000 比区域提案网络（RPN）高 14.5%，超越了所有现有的区域提案方法。我们还将 SC-RPN 集成到 Fast R-CNN 和 Faster R-CNN 中来测试其在目标检测任务上的有效性，实验结果与原始结果相比，在 mAP 方面分别获得了 3.2% 和 3.8% 的增益。