# SFPN: Synthetic FPN for Object Detection

Source: [SFPN: Synthetic FPN for Object Detection](<https://www.sota2.com/research/paper/68fa6bf71e209131cea314f1>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-10-26T00:00:55.020Z

Authors: Yu-Ming Zhang, Jun-Wei Hsieh, Chun-Chieh Lee, Kuo-Chin Fan

Published: 2022-03-04T17:19:50.000Z

## Abstract

FPN (Feature Pyramid Network) has become a basic component of most SoTA one stage object detectors. Many previous studies have repeatedly proved that FPN can caputre better multi-scale feature maps to more precisely describe objects if they are with different sizes. However, for most backbones such VGG, ResNet, or DenseNet, the feature maps at each layer are downsized to their quarters due to the pooling operation or convolutions with stride 2. The gap of down-scaling-by-2 is large and makes its FPN not fuse the features smoothly. This paper proposes a new SFPN (Synthetic Fusion Pyramid Network) arichtecture which creates various synthetic layers between layers of the original FPN to enhance the accuracy of light-weight CNN backones to extract objects' visual features more accurately. Finally, experiments prove the SFPN architecture outperforms either the large backbone VGG16, ResNet50 or light-weight backbones such as MobilenetV2 based on AP score.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2203.02445>)

[PDF](<https://arxiv.org/pdf/2203.02445.pdf>)
