欢迎您访问程序员文章站本站旨在为大家提供分享程序员计算机编程知识!
您现在的位置是: 首页  >  IT编程

AI实战:一种新的深度目标检测架构 Matrix Nets

程序员文章站 2022-03-26 14:57:12
Matrix Nets: A New Deep Architecture for Object DetectionAP在MS COCO上实现了47.8的mAPAP比较Matrix Networks(a) Shows the original FPN architecture(b) Shows the MatrixNet architecture, where the 5 FPN layers are viewed as the diagonal layers in the mat...

Matrix Nets: A New Deep Architecture for Object Detection

  • AP
    在MS COCO上实现了47.8的mAP

  • AP比较
    AI实战:一种新的深度目标检测架构 Matrix Nets

  • Matrix Networks

    AI实战:一种新的深度目标检测架构 Matrix Nets

    (a) Shows the original FPN architecture
    (b) Shows the MatrixNet architecture, where the 5 FPN layers are viewed as the diagonal layers in the matrix. We fill in the rest of the matrix by downsampling these layers.

  • KP-xNet architecture

    AI实战:一种新的深度目标检测架构 Matrix Nets

  • 实验结果
    Empirical results on MSCOCO for our method as compared to best results reported in other works.

    AI实战:一种新的深度目标检测架构 Matrix Nets

  • 其他详细细节可以参考原论文

  • 论文链接:Matrix Nets: A New Deep Architecture for Object Detection

  • 开源代码

    pytorch版 MatrixNets 实现: https://github.com/arashwan/matrixnet (包含了 train、 test 代码)

本文地址:https://blog.csdn.net/zengNLP/article/details/107573363