2019 | Anchor-free的对象检测网络汇总
点击上方↑↑↑“OpenCV学堂”关注我
关注我们,技术干货,行业动态第一时间送达
论文
从去年第开始,在深度学习的对象检测技术方向,刮起了一阵anchor-free网络模型的旋风,涌现出了很多anchor-free的对象检测网络模型。相关论文收集整理,汇总如下方便大家查阅:
CornerNet
CornerNet: Keypoint Triplets for Object Detection
https://arxiv.org/pdf/1808.01244.pdfExtremeNet
Bottom-up Object Detection by Grouping Extreme and Center Points
https://arxiv.org/pdf/1901.08043.pdfCornerNet-Lite
CornerNet-Lite: Efficient Keypoint Based Object Detection
https://arxiv.org/pdf/1904.08900.pdfSegmentations is All You Need
https://arxiv.org/pdf/1904.13300.pdfFCOS
Fully Convolutional One-Stage Object Detection
https://arxiv.org/abs/1904.01355.pdfFovea|FoveaBox:
Beyond Anchor-based Object Detector
https://arxiv.org/pdf/1904.03797.pdfCenterNet^1
Objects as Points
https://arxiv.org/pdf/1904.07850.pdfCenterNet^2
CenterNet: Keypoint Triplets for Object Detection
https://arxiv.org/pdf/1904.08189.pdfDuBox|DuBox:
No-Prior Box Objection Detection via Residual Dual Scale Detectors
https://arxiv.org/pdf/1904.06883.pdfRepPoints|RepPoints:
Point Set Representation for Object Detection
https://arxiv.org/pdf/1904.11490.pdfFSAF
Feature Selective Anchor-Free Module for Single-Shot Object Detection
https://arxiv.org/pdf/1903.00621.pdfDenseBox|DenseBox:
Unifying Landmark Localization with End to End Object Detection
https://arxiv.org/pdf/1509.04874.pdfAF-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
代码资源
相关的源码实现如下,大家去github上git clone一波,多数都是基于pytorch框架的,说明pytorch最近势头很猛!
CornerNet| (official, Pytorch)
https://github.com/princeton-vl/CornerNetCornerNet-Lite| (official, Pytorch)
https://github.com/princeton-vl/CornerNet-LiteFCOS| (official, Pytorch)
https://github.com/tianzhi0549/FCOSCenterNet^1| (official, Pytorch)
https://github.com/xingyizhou/CenterNetCenterNet^2| (official, pytorch)
https://github.com/Duankaiwen/CenterNetExtremeNet| (official, Pytorch)
https://github.com/xingyizhou/ExtremeNet
往期精选
告诉大家你在看