AugFCOS: Augmented fully convolutional one-stage object detection network

作者：

Highlights：

• A Robust Training Sample Selection strategy is proposed to effectively solve the problem of hyperparameter dependence.

• Mitigate the impact of centerness loss without decreasing by designing a dynamic optimization loss.

• A mixed attention module is proposed to enhance the multi-scale representation ability of feature pyramids.

摘要

•A Robust Training Sample Selection strategy is proposed to effectively solve the problem of hyperparameter dependence.•Mitigate the impact of centerness loss without decreasing by designing a dynamic optimization loss.•A mixed attention module is proposed to enhance the multi-scale representation ability of feature pyramids.

论文关键词：Feature pyramid network,Object detection,Sample selection,Attention module

论文评审过程：Received 27 April 2022, Revised 16 August 2022, Accepted 4 October 2022, Available online 7 October 2022, Version of Record 13 October 2022.

论文官网地址：https://doi.org/10.1016/j.patcog.2022.109098