# AGSFCOS: Based on attention mechanism and Scale-Equalizing pyramid network of object detection

Source: [AGSFCOS: Based on attention mechanism and Scale-Equalizing pyramid network of object detection](<https://www.sota2.com/research/paper/68fa6a051e209131cea257b8>)

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

Data updated: 2025-10-25T23:14:37.392Z

Authors: Li Wang, Wei Xiang, Ruhui Xue, Kaida Zou, Laili Zhu

Published: 2021-05-20T08:41:02.000Z

## Abstract

Recently, the anchor-free object detection model has shown great potential for accuracy and speed to exceed anchor-based object detection. Therefore, two issues are mainly studied in this article: (1) How to let the backbone network in the anchor-free object detection model learn feature extraction? (2) How to make better use of the feature pyramid network? In order to solve the above problems, Experiments show that our model has a certain improvement in accuracy compared with the current popular detection models on the COCO dataset, the designed attention mechanism module can capture contextual information well, improve detection accuracy, and use sepc network to help balance abstract and detailed information, and reduce the problem of semantic gap in the feature pyramid network. Whether it is anchor-based network model YOLOv3, Faster RCNN, or anchor-free network model Foveabox, FSAF, FCOS. Our optimal model can get 39.5% COCO AP under the background of ResNet50.

## 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/2105.09596>)

[PDF](<https://arxiv.org/pdf/2105.09596.pdf>)