Anchor-free的目標檢測網絡彙總

1、文章彙總

  • CornerNet
    CornerNet: Keypoint Triplets for Object Detection
    https://arxiv.org/pdf/1808.01244.pdf

  • ExtremeNet
    Bottom-up Object Detection by Grouping Extreme and Center Points
    https://arxiv.org/pdf/1901.08043.pdf

  • CornerNet-Lite
    CornerNet-Lite: Efficient Keypoint Based Object Detection
    https://arxiv.org/pdf/1904.08900.pdf

  • Segmentations is All You Need
    https://arxiv.org/pdf/1904.13300.pdf

  • FCOS
    Fully Convolutional One-Stage Object Detection
    https://arxiv.org/abs/1904.01355.pdf

  • Fovea|FoveaBox: 
    Beyond Anchor-based Object Detector
    https://arxiv.org/pdf/1904.03797.pdf

  • CenterNet^1
    Objects as Points
    https://arxiv.org/pdf/1904.07850.pdf

  • CenterNet^2
    CenterNet: Keypoint Triplets for Object Detection
    https://arxiv.org/pdf/1904.08189.pdf

  • DuBox|DuBox: 
    No-Prior Box Objection Detection via Residual Dual Scale Detectors
    https://arxiv.org/pdf/1904.06883.pdf

  • RepPoints|RepPoints: 
    Point Set Representation for Object Detection
    https://arxiv.org/pdf/1904.11490.pdf

  • FSAF
    Feature Selective Anchor-Free Module for Single-Shot Object Detection
    https://arxiv.org/pdf/1903.00621.pdf

  • DenseBox|DenseBox: 
    Unifying Landmark Localization with End to End Object Detection
    https://arxiv.org/pdf/1509.04874.pdf

  • AF-RPN
    An Anchor-Free Region Proposal Network for Faster R-CNN based Text Detection Approaches
    https://arxiv.org/ftp/arxiv/papers/1804/1804.09003.pdf

2、代碼彙總

     多數都是基於pytorch框架的

  • CornerNet| (official, Pytorch)
    https://github.com/princeton-vl/CornerNet

  • CornerNet-Lite| (official, Pytorch)
    https://github.com/princeton-vl/CornerNet-Lite

  • FCOS| (official, Pytorch)
    https://github.com/tianzhi0549/FCOS

  • CenterNet^1| (official, Pytorch)
    https://github.com/xingyizhou/CenterNet

  • CenterNet^2| (official, pytorch)
    https://github.com/Duankaiwen/CenterNet

  • ExtremeNet| (official, Pytorch)
    https://github.com/xingyizhou/ExtremeNet

 

發表評論
所有評論
還沒有人評論,想成為第一個評論的人麼? 請在上方評論欄輸入並且點擊發布.
相關文章