This paper proposes the Parallel Residual Bi-Fusion Feature Pyramid Network (PRB-FPN) for fast and accurate single-shot object detection. Feature Pyramid (FP) is widely used in recent visual detection, however the top-down pathway of FP cannot preserve accurate localization due to pooling shifting. The advantage of FP is weakened as deeper backbones with more layers are used. In addition, it cannot keep up accurate detection of both small and large objects at the same time. To address these issues, we propose a new parallel FP structure with bi-directional (top-down and bottom-up) fusion and associated improvements to retain high-quality features for accurate localization. We provide the following design improvements: (1) A parallel bifusion FP structure with a bottom-up fusion module (BFM) to detect both small and large objects at once with high accuracy. (2) A concatenation and re-organization (CORE) module provides a bottom-up pathway for feature fusion, which leads to the bi-directional fusion FP that can recover lost information from lower-layer feature maps. (3) The CORE feature is further purified to retain richer contextual information. Such CORE purification in both top-down and bottom-up pathways can be finished in only a few iterations. (4) The adding of a residual design to CORE leads to a new Re-CORE module that enables easy training and integration with a wide range of deeper or lighter backbones. The proposed network achieves state-of-the-art performance on the UAVDT17 and MS COCO datasets. Code is available at https://github.com/pingyang1117/PRBNet_PyTorch.

翻译：本文提出并行残差双融合特征金字塔网络(PRB-FPN)，用于快速且精确的单阶段目标检测。特征金字塔(FP)在近年来的视觉检测中被广泛应用，然而FP的顶层向下路径由于池化偏移无法保持精确定位。随着使用更多层的更深骨干网络，FP的优势被削弱。此外，它无法同时保持对小目标和大型目标的精确检测。为解决这些问题，我们提出一种新的并行FP结构，采用双向（顶层向下和底层向上）融合及相应改进来保留用于精确定位的高质量特征。我们提供以下设计改进：(1) 一种带有底层向上融合模块(BFM)的并行双融合FP结构，可同时高精度检测小目标和大型目标。(2) 一个拼接重组(CORE)模块提供用于特征融合的底层向上路径，从而形成双向融合FP，能够从低层特征图中恢复丢失信息。(3) 对CORE特征进一步净化以保留更丰富的上下文信息。这种在顶层向下和底层向上路径中的CORE净化只需少量迭代即可完成。(4) 在CORE中添加残差设计形成新的Re-CORE模块，便于训练并与多种更深或更轻骨干网络集成。所提网络在UAVDT17和MS COCO数据集上达到最先进性能。代码可在https://github.com/pingyang1117/PRBNet_PyTorch获取。