基于Anchor Free的目标检测

这篇博客汇总了近期深度学习在目标检测领域的多个先进模型,包括YOLO、CornerNet、CenterNet等,详细介绍了它们的论文、代码实现和解析。这些模型通过不同的方法提升了目标检测的精度和效率,例如 CornerNet 使用关键点检测,CenterNet 则将对象视为点,简化了检测过程。此外,还提到了Generalized Focal Loss等损失函数的改进,以优化训练过程。
摘要由CSDN通过智能技术生成

总结:https://blog.csdn.net/weixin_36670529/article/details/106468834
1.UnitBox: An Advanced Object Detection Network
论文:
代码:
解析:
2.DenseBox: Unifying Landmark Localization and Object Detection
论文:
代码:
解析:
3.You Only Look Once (YOLO) for Object Detection (YOLOV1)
论文:
代码:
解析:
4.CornerNet: Detecting Objects as Paired Keypoints
论文:https://arxiv.org/abs/1808.01244
代码:https://github.com/umich-vl/CornerNet
解析:https://blog.csdn.net/qq_38109843/article/details/89526785
5.ExtremeNet: Bottom-up Object Detection by Grouping Extreme and Center Points
论文:
代码:
解析:
6.FSAF: Feature Selective Anchor-Free Module
论文:
代码:
解析:
7.FCOS: Fully Convolutional One-Stage Object Detection
论文:https://arxiv.org/abs/1904.01355
代码:https://github.com/tianzhi0549/FCOS/
解析:https://blog.csdn.net/chunfengyanyulove/article/details/95091061https://zhuanlan.zhihu.com/p/63868458
8.FoveaBox: Beyond Anchor-based Object Detector
论文:
代码:
解析:
9.Region Proposal by Guided Anchoring (GA-RPN)
论文:
代码:
解析:
10.CenterNet: Objects as Points
论文:https://arxiv.org/pdf/1904.07850.pdf
代码:https://github.com/xingyizhou/CenterNet
解析:https://blog.csdn.net/qq_38109843/article/details/104669901
11.CenterNet: Object Detection with Keypoint Triplets
论文:https://arxiv.org/abs/1904.08189
代码:https://github.com/Duankaiwen/CenterNet
解析:https://www.cnblogs.com/gawain-ma/archive/2019/05/17/10882113.html
12.CornerNet-Lite:CornerNet-Saccade(attention mechanism)+ CornerNet-Squeeze
论文:https://arxiv.org/pdf/1904.08900.pdf
代码:https://github.com/princeton-vl/CornerNet-Lite
解析:https://blog.csdn.net/qq_38109843/article/details/90898710
13.Center and Scale Prediction: A Box-free Approach for Object Detection
论文:
代码:
解析:
14.Generalized Focal Loss
论文:https://arxiv.org/pdf/2006.04388.pdf
代码:https://github.com/implus/GFocalhttps://github.com/open-mmlab/mmdetection/blob/master/configs/gfl/README.md
解析:https://zhuanlan.zhihu.com/p/147691786
15.Generalized Focal Loss v2
论文:https://arxiv.org/pdf/2011.12885.pdf
代码:https://github.com/implus/GFocalV2
解析:https://zhuanlan.zhihu.com/p/313684358?utm_source=ZHShareTargetIDMore

开源项目:
1.Nanodet
代码:https://github.com/RangiLyu/nanodet
解析:https://zhuanlan.zhihu.com/p/306530300

  • 1
    点赞
  • 6
    收藏
    觉得还不错? 一键收藏
  • 1
    评论
评论 1
添加红包

请填写红包祝福语或标题

红包个数最小为10个

红包金额最低5元

当前余额3.43前往充值 >
需支付:10.00
成就一亿技术人!
领取后你会自动成为博主和红包主的粉丝 规则
hope_wisdom
发出的红包
实付
使用余额支付
点击重新获取
扫码支付
钱包余额 0

抵扣说明:

1.余额是钱包充值的虚拟货币,按照1:1的比例进行支付金额的抵扣。
2.余额无法直接购买下载,可以购买VIP、付费专栏及课程。

余额充值