最全目标检测相关资料整理 (目标检测+数据增强+卷价神经网络+类别不均衡...)

1 小目标检测:

综述:

综述论文Augmentation for small object detection

深度学习笔记(十)Augmentation for small object detection(翻译)

吴建明wujianning:小目标检测的增强算法

机器之心:什么是小样本学习?这篇综述文章用166篇参考文献告诉你答案

2 目标检测

论文追踪:github.com/amusi/awesom

综述文章:

1) Object Detection in 20 Years: A Survey

论文下载:arxiv.org/abs/1905.0505

论文阅读:论文笔记-2019-Object Detection in 20 Years: A Survey

2)A Survey of Deep Learning-based Object Detection

论文下载:arxiv.org/abs/1907.0940

论文阅读:墨仆:读 A Survey of Deep Learning-based Object Detection

3)Recent Advances in Deep Learning for Object Detection

论文下载:arxiv.org/abs/1908.0367

论文阅读:一个啥都不会的程序猿:目标检测综述-Deep Learning for Object Detection(一)

4)Deep Learning for Generic Object Detection: A Survey

论文下载:Deep Learning for Generic Object Detection: A Survey

论文阅读:Deep Learning for Generic Object Detection: A Survey -- 目标检测综述总结

跑者小越:私藏多年的目标检测好文分享 (不收藏血亏)

3 数据增强

chaser:A survey on Image Data Augmentation 数据增强文献综述 zhuanlan.zhihu.com图标 CrazyVertigo:数据增强方法 zhuanlan.zhihu.com图标 CrazyVertigo:GridMask Data Augmentation zhuanlan.zhihu.com图标 https://github.com/CrazyVertigo/awesome-data-augmentation github.com
Tom Hardy:汇总|目标检测中的数据增强、backbone、head、neck、损失函数 zhuanlan.zhihu.com图标

4 卷积神经网络

1)

论文地址:arxiv.org/abs/1803.0883

94页论文综述卷积神经网络:从基础技术到研究前景

2)A Survey of the Recent Architectures of Deep Convolutional Neural Networks

论文阅读:Deep learning_CNN_Review:A Survey of the Recent Architectures of Deep Convolutional Neural Networks--2019

论文下载:A Survey of the Recent Architectures of Deep Convolutional Neural Networks

5 类别不均衡

ChenJoya:Imbalance Problems in Object Detection: A Review

github.com/kemaloksuz/O

鑫鑫淼淼焱焱:类别不平衡学习资源推荐

ZhiningLiu1998/awesome-imbalanced-learning

6 关于深度学习优化方法

1)mp.weixin.qq.com/s/hbJj

2)链接:pan.baidu.com/s/1DCQYTf 密码:x22d

7 NMS

Adaptive NMS: Refining Pedestrian Detection in a Crowd

论文阅读:论文阅读2(CVPR2019):Adaptive NMS:Refining Pedestrian Detection in a Crowd

论文下载:Adaptive NMS: Refining Pedestrian Detection in a Crowd

8 模型训练

1) Bag of Freebies for Training Object Detection Neural Networks

论文下载:Bag of Freebies for Training Object Detection Neural Networks

论文阅读:

李沐等将目标检测绝对精度提升 5%,不牺牲推理速度 www.jiqizhixin.com图标


sticky:深度学习 cnn trick合集 zhuanlan.zhihu.com图标

9 目标检测中attention

1)Relation Networks for Object Detection

论文阅读:Relation Networks for Object Detection算法笔记

论文下载;Relation Networks for Object Detection

10)IoU

CrazyVertigo:目标检测回归损失函数简介:SmoothL1/IoU/GIoU/DIoU/CIoU Loss zhuanlan.zhihu.com图标

11)模型加速

CrazyVertigo:【模型压缩和加速】inception/mobilenet/squeezenet/shuffle zhuanlan.zhihu.com图标 简枫:一文看懂深度学习模型压缩和加速 zhuanlan.zhihu.com图标

12)实验效率及可视化

LiuFG:提高DL实验效率神器初体验-fitlog/nni/determind zhuanlan.zhihu.com图标

13)小目标学习


机器之心:什么是小样本学习?这篇综述文章用166篇参考文献告诉你答案 zhuanlan.zhihu.com图标

14)目标检测tricks

zhuanlan.zhihu.com/p/14

初识CV:目标检测比赛中的tricks(已更新更多代码解析) zhuanlan.zhihu.com图标 roger:目标检测中的Tricks zhuanlan.zhihu.com图标

未完待续!!!

原文链接:https://zhuanlan.zhihu.com/p/136206896
  • 0
    点赞
  • 7
    收藏
    觉得还不错? 一键收藏
  • 0
    评论
评论
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