1、基础
  自己对于YOLOV1,2,3都比较熟悉。 RCNN也比较熟悉。这个是自己目前掌握的基础
2、第一步
  看一下2019年的井喷的anchor free的网络
3、第二步
  看一下以往,引用多的网路
4、第三步
  看一下,2020最新的,但是在pwcode上面排名靠前的网络

2020优秀论文:
EfficientDet: Scalable and Efficient Object Detection,57
DetectoRS: Detecting Objects with Recursive Feature Pyramid and Switchable Atrous Convolution
Rethinking Pre-training and Self-training
Revisiting the Sibling Head in Object Detector
Deep High-Resolution Representation Learning for Visual Recognition*52
HoughNet: Integrating near and long-range evidence for bottom-up object detection ??
M2Det: A Single-Shot Object Detector based on Multi-Level Feature Pyramid Network,101

优秀论文:
Acquisition of Localization Confidence for Accurate Object Detection,182
Scale-Aware Trident Networks for Object Detection,141
GCNet: Non-local Networks Meet Squeeze-Excitation Networks and Beyond,107
Path Aggregation Network for Instance Segmentation,400
Hybrid Task Cascade for Instance Segmentation ,139
SNIPER: Efficient Multi-Scale Training,141
Deformable ConvNets v2: More Deformable, Better Results,188
An Analysis of Scale Invariance in Object Detection - SNIP,218
Single-Shot Refinement Neural Network for Object Detection,414
Attention Augmented Convolutional Networks,58
SaccadeNet: A Fast and Accurate Object Detector

two stage:
Grid R-CNN, plus,46
Cascade R-CNN: Delving into High Quality Object Detection,571
Libra R-CNN: Towards Balanced Learning for Object Detection,115
Dynamic R-CNN: Towards High Quality Object Detection via Dynamic Training

one stage:
ExtremNet :Bottom-up Object Detection by Grouping Extreme and Center Points 2019,129
YoLOV5
YOLOv4: Optimal Speed and Accuracy of Object Detection*,17

anchor free的网络:
Scale-Equalizing Pyramid Convolution for Object Detection,2020
FoveaBox: Beyond Anchor-based Object Detector 2019,52
CornerNet: Detecting Objects as Paired Keypoints 2018 ,445
CornerNet-Lite (2019) (https://arxiv.org/abs/1904.08900)
CenterNet: Keypoint Triplets for Object Detection 2019,129
FCOS: Fully Convolutional One-Stage Object Detection 2019,206
Feature Selective Anchor-Free Module for Single-Shot Object Detection,144

object detection 总结的更多相关文章

  1. tensorfolw配置过程中遇到的一些问题及其解决过程的记录(配置SqueezeDet: Unified, Small, Low Power Fully Convolutional Neural Networks for Real-Time Object Detection for Autonomous Driving)

    今天看到一篇关于检测的论文<SqueezeDet: Unified, Small, Low Power Fully Convolutional Neural Networks for Real- ...

  2. 论文阅读(Chenyi Chen——【ACCV2016】R-CNN for Small Object Detection)

    Chenyi Chen--[ACCV2016]R-CNN for Small Object Detection 目录 作者和相关链接 方法概括 创新点和贡献 方法细节 实验结果 总结与收获点 参考文献 ...

  3. deep learning on object detection

    回归工作一周,忙的头晕,看了两三篇文章,主要在写各种文档和走各种办事流程了-- 这次来写写object detection最近看的三篇文章吧.都不是最近的文章,但是是今年的文章,我也想借此让自己赶快熟 ...

  4. 论文阅读之 DECOLOR: Moving Object Detection by Detecting Contiguous Outliers in the Low-Rank Representation

    DECOLOR: Moving Object Detection by Detecting Contiguous Outliers in the Low-Rank Representation Xia ...

  5. 目标检测--Rich feature hierarchies for accurate object detection and semantic segmentation(CVPR 2014)

    Rich feature hierarchies for accurate object detection and semantic segmentation 作者: Ross Girshick J ...

  6. object detection技术演进:RCNN、Fast RCNN、Faster RCNN

    object detection我的理解,就是在给定的图片中精确找到物体所在位置,并标注出物体的类别.object detection要解决的问题就是物体在哪里,是什么这整个流程的问题.然而,这个问题 ...

  7. TensorFlow Object Detection API(Windows下测试)

    "Speed/accuracy trade-offs for modern convolutional object detectors." Huang J, Rathod V, ...

  8. Object Detection · RCNN论文解读

    转载请注明作者:梦里茶 Object Detection,顾名思义就是从图像中检测出目标对象,具体而言是找到对象的位置,常见的数据集是PASCAL VOC系列.2010年-2012年,Object D ...

  9. 使用TensorFlow Object Detection API+Google ML Engine训练自己的手掌识别器

    上次使用Google ML Engine跑了一下TensorFlow Object Detection API中的Quick Start(http://www.cnblogs.com/take-fet ...

  10. Object Detection︱RCNN、faster-RCNN框架的浅读与延伸内容笔记

    一.RCNN,fast-RCNN.faster-RCNN进化史 本节由CDA深度学习课堂,唐宇迪老师教课,非常感谢唐老师课程中的论文解读,很有帮助. . 1.Selective search 如何寻找 ...

随机推荐

  1. cnn卷积理解

    首先输入图像是28*28处理好的图. 第一层卷积:用5*5的卷积核进行卷积,输入为1通道,输出为32通道.即第一层的输入为:28*28图,第一层有32个不同的滤波器,对同一张图进行卷积,然后输出为32 ...

  2. Cordova总是弹出Connection to server was Unsuccessful

    开发环境:Cordova版本:6.x 安卓版本:6.0 解决方案一: 在config.xml中添加以下内容: <preference name="LoadUrlTimeoutValue ...

  3. 2.5万字长文简单总结SpringMVC请求参数接收

    这是公众号<Throwable文摘>发布的第22篇原创文章,暂时收录于专辑<架构与实战>.暂定下一篇发布的长文是<图文分析JUC同步器框架>,下一篇发布的短文是&l ...

  4. javascript算法 最短路径问题

    var obj = { 1: [2, 3], 2: [1, 4, 5], 3: [1, 7, 8], 4: [2, 7], 7: [4, 8], } var 起点 = 1 var 终点 = 8 var ...

  5. 细说websocket快速重连机制

    文|马莹莹 网易智慧企业web前端开发工程师 引言 在一个完善的即时通讯应用中,websocket是极其关键的一环,它为web应用的客户端和服务端提供了一种全双工的通信机制,但由于它本身以及其底层依赖 ...

  6. 使样式只在webkit内核生效

    @media screen and (-webkit-min-device-pixel-ratio:0){ .do someting{ } }     使用媒体查询,制定样式

  7. 前端学习(五):body标签(三)

    进击のpython ***** 前端学习--body标签 接下来的内容就比较多了,各位看官且听我慢慢道来... ... 使用a标签,链接到另一个页面 网页中<a>标签,全称:anchor. ...

  8. sed 指定行范围匹配

    sed -n '5,10{/pattern/p}' file sed是一个非交互性性文本编辑器,它编辑文件或标准输入 导出的文件拷贝.标准输入可能是来自键盘.文件重定向.字符串或变量,或者是一个管道文 ...

  9. cpp求职

    //Created by Arc on 2020/5/23 //////// Created by snnnow on 2020/5/20.//////面向对象的程序设计-期中测试// 根据题目实现求 ...

  10. jquery判断radio是否选中

    微交易-实体系统 微交易-虚拟系统   <div class="system"> <div class="systemt"> <l ...