Parallel Residual Bi-Fusion Feature Pyramid Network for Accurate Single-Shot Object Detection

3 Dec 2020  ·  Ping-Yang Chen, Ming-Ching Chang, Jun-Wei Hsieh, Yong-Sheng Chen ·

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

PDF Abstract


Results from the Paper

Task Dataset Model Metric Name Metric Value Global Rank Result Benchmark
Real-Time Object Detection MS COCO PRB-FPN6-E-ELAN FPS (V100, b=1) 31 # 21
box AP 56.9 # 2
FPS 31 # 22
Real-Time Object Detection MS COCO PRB-FPN-ELAN FPS (V100, b=1) 70 # 15
box AP 52.5 # 26
FPS 70 # 13
Real-Time Object Detection MS COCO PRB-FPN-MSP FPS (V100, b=1) 94 # 11
box AP 53.3 # 17
FPS 94 # 9
Real-Time Object Detection MS COCO PRB-FPN-CSP FPS (V100, b=1) 113 # 10
box AP 51.8 # 28
FPS 113 # 8
Object Detection UAVDT PRB-FPN mAP 76.55 # 1


No methods listed for this paper. Add relevant methods here