MFPN: A Novel Mixture Feature Pyramid Network of Multiple Architectures for Object Detection
This work improves object detection accuracy for computer vision applications, but it is incremental as it builds on existing FPN methods.
The paper tackles the scale variation problem in object detection by proposing a Mixture Feature Pyramid Network (MFPN) that combines three FPN architectures, achieving about a 2% AP increase on the MS-COCO benchmark with minimal latency impact.
Feature pyramids are widely exploited in many detectors to solve the scale variation problem for object detection. In this paper, we first investigate the Feature Pyramid Network (FPN) architectures and briefly categorize them into three typical fashions: top-down, bottom-up and fusing-splitting, which have their own merits for detecting small objects, large objects, and medium-sized objects, respectively. Further, we design three FPNs of different architectures and propose a novel Mixture Feature Pyramid Network (MFPN) which inherits the merits of all these three kinds of FPNs, by assembling the three kinds of FPNs in a parallel multi-branch architecture and mixing the features. MFPN can significantly enhance both one-stage and two-stage FPN-based detectors with about 2 percent Average Precision(AP) increment on the MS-COCO benchmark, at little sacrifice in running time latency. By simply assembling MFPN with the one-stage and two-stage baseline detectors, we achieve competitive single-model detection results on the COCO detection benchmark without bells and whistles.