Object proposals are used in two-stage detectors, such as R-CNN, to generate detection results, including category predictions and refined bounding-boxes. As a result, classification scores are assigned to refined bounding-boxes rather than object proposals. However, this procedure ignores the discrepancy of data distribution between object proposals and refined bounding-boxes. We consider this discrepancy could limit the detection accuracy. Specifically, the foreground/background imbalance on object proposals and inaccurate information from low-IoU proposals could hinder the category prediction. In this paper, we propose a detector called the Multi-Path Detection Calibration Network (PDC-Net) to address this problem. The key idea behind PDC-Net is calibrating detection results from R-CNN by considering the statistical discrepancy between object proposals and refined bounding-boxes. PDC-Net is built on Faster R-CNN. The core component in PDC-Net is the multi-path detection head, in which the base detector (from Faster R-CNN) generates detection results from object proposals and multiple calibration detectors fix incorrect outputs from the base detector using refined bounding-boxes. Experiments reveal that PDC-Net can boost detection results. Our method could reach 83.1% and 43.3% mAP respectively on PASCAL VOC and MSCOCO benchmarks, which is comparable to several state-of-the-art methods.

中文翻译：

---

使用多路径检测校准网络进行高质量 R-CNN 目标检测


对象提议用于两级检测器（例如 R-CNN）中，以生成检测结果，包括类别预测和细化边界框。因此，分类分数被分配给细化的边界框而不是对象建议。然而，该过程忽略了对象建议和细化边界框之间的数据分布差异。我们认为这种差异可能会限制检测的准确性。具体来说，对象提案的前景/背景不平衡以及低 IoU 提案的不准确信息可能会阻碍类别预测。在本文中，我们提出了一种称为多路径检测校准网络（PDC-Net）的检测器来解决这个问题。 PDC-Net 背后的关键思想是通过考虑目标提议和细化边界框之间的统计差异来校准 R-CNN 的检测结果。 PDC-Net 建立在 Faster R-CNN 之上。 PDC-Net 的核心组件是多路径检测头，其中基础检测器（来自 Faster R-CNN）根据目标提案生成检测结果，多个校准检测器使用精细的边界框修复基础检测器的错误输出。实验表明 PDC-Net 可以提高检测结果。我们的方法在 PASCAL VOC 和 MSCOCO 基准上分别达到 83.1% 和 43.3% mAP，这与几种最先进的方法相当。