# Object Detection 文章整理

:::info
大概從網路上找了幾篇中文的文章方便理解，並且主觀的作了大方向的分類。
雖然分了大方向，但講同一件事情的文章有許多，這裡只抓了 Google 到的前幾篇。極有可能會一直看到同樣的論述或名詞，反正不管，多看多健康!

假如中括號來源後面有 *斜線* 標註作者，代表我認為此文章可能是同作者的系列文章或是大專欄裡面的某一篇，又或者是同作者也有相關主題並且是我覺得值得做延伸閱讀的，非常推薦同時服用。
:::

### 偏概念講解

:::info
以下幾篇主要針對 Object Detection 的概念，文章中可能會提及某些經典模型，可以服用完畢後再去看模型的細節
:::

* [Medium/Tommy Huang](https://chih-sheng-huang821.medium.com/)
* [深度學習-什麼是one stage，什麼是two stage 物件偵測](https://chih-sheng-huang821.medium.com/%E6%B7%B1%E5%BA%A6%E5%AD%B8%E7%BF%92-%E4%BB%80%E9%BA%BC%E6%98%AFone-stage-%E4%BB%80%E9%BA%BC%E6%98%AFtwo-stage-%E7%89%A9%E4%BB%B6%E5%81%B5%E6%B8%AC-fc3ce505390f)
* [深度學習: 物件偵測上的模型結構變化](https://chih-sheng-huang821.medium.com/%E6%B7%B1%E5%BA%A6%E5%AD%B8%E7%BF%92-%E7%89%A9%E4%BB%B6%E5%81%B5%E6%B8%AC%E4%B8%8A%E7%9A%84%E6%A8%A1%E5%9E%8B%E7%B5%90%E6%A7%8B%E8%AE%8A%E5%8C%96-e23fd928ee59)
* [Medium/李謦伊](https://medium.com/@chingi071)
* [物件偵測 Object Detection 概述](https://medium.com/ching-i/%E7%89%A9%E4%BB%B6%E5%81%B5%E6%B8%AC-object-detection-%E6%A6%82%E8%BF%B0-d4f71cafcd77)
* [CSDN/三十八元](https://blog.csdn.net/sanshibayuan?type=blog)
* [目标检测（Object Detection）学习笔记（一）目标检测综述](https://blog.csdn.net/sanshibayuan/article/details/103644610)
* ~~[[知乎/NeoAndrew] 五、目标检测基础和概念与术语](https://zhuanlan.zhihu.com/p/510643609)~~ [已失效]
* [知乎/yanwan](https://www.zhihu.com/people/tfygg/posts)
* [The Battle of One-Stage vs Two-Stage Detection](https://zhuanlan.zhihu.com/p/161194349)
* [图解目标检测 系列文章](https://zhuanlan.zhihu.com/p/151829072)

### Anchor 概念

* Anchor-base
* [[CSDN/三十八元] 目标检测（Object Detection）学习笔记（二）Anchor-Based经典检测模型（Faster R-CNN、YOLO、SSD）](https://blog.csdn.net/sanshibayuan/article/details/103644826)

* Anchor-free
* [[CSDN/三十八元] 目标检测（Object Detection）学习笔记（三）Anchor-Free检测模型与方法](https://blog.csdn.net/sanshibayuan/article/details/103653942)
* [Medium/Jia-Yau Shiau](https://jiayaushiau.medium.com/)
* [Object Detection 錨點之爭： Anchor Free大爆發的2019年](https://medium.com/ai-blog-tw/cv-object-detection-1-anchor-free%E5%A4%A7%E7%88%86%E7%99%BC%E7%9A%842019%E5%B9%B4-e3b4271cdf1a)
* [通往Anchor-Free的真相：Object Detection的正負樣本定義](https://medium.com/ai-blog-tw/%E9%80%9A%E5%BE%80anchor-free%E7%9A%84%E7%9C%9F%E7%9B%B8-object-detection%E7%9A%84%E6%AD%A3%E8%B2%A0%E6%A8%A3%E6%9C%AC%E5%AE%9A%E7%BE%A9-83f2fe36167f)
* ~~[[知乎/NeoAndrew] 五、Anchor-free模型崛起](https://zhuanlan.zhihu.com/p/510655111)~~ [已失效]
* [[知乎/陀飞轮] 目标检测：Anchor-Free时代](https://zhuanlan.zhihu.com/p/62103812)

### 經典模型介紹

* ~~[[知乎/NeoAndrew] R-CNN家族](https://zhuanlan.zhihu.com/p/510645613)~~ [已失效]

* SSD
* [SSD: Single Shot MultiBox Detector 介紹](https://medium.com/@bigwaterking01/ssd-single-shot-multibox-detector-%E4%BB%8B%E7%B4%B9-1fe95073c1a3)
* [目标检测|SSD原理与实现](https://zhuanlan.zhihu.com/p/33544892)

* YOLO
* [[Medium/Tommy Huang] 深度學習-物件偵測:You Only Look Once (YOLO)](https://chih-sheng-huang821.medium.com/%E6%B7%B1%E5%BA%A6%E5%AD%B8%E7%BF%92-%E7%89%A9%E4%BB%B6%E5%81%B5%E6%B8%AC-you-only-look-once-yolo-4fb9cf49453c).
* ~~[[知乎/NeoAndrew] 五、目标检测：one-stage始祖YOLO](https://zhuanlan.zhihu.com/p/510647289)~~ [已失效]

* CornerNet
* [[iThome/AlittleQ] Epoch 6 - 物件辨識論文筆記 x CornerNet](https://ithelp.ithome.com.tw/articles/10238002)
* [[iThome/AlittleQ] Epoch 7 - 物件辨識論文筆記 x CornerNet-Lite](https://ithelp.ithome.com.tw/articles/10238844)

* CenterNet
* [[機器之心] 论文也撞衫，你更喜欢哪个无锚点CenterNet？](https://www.jiqizhixin.com/articles/2019-09-17-6)
* [[CSDN/bryant_meng] 【CenterNet】《Objects as Points](https://blog.csdn.net/bryant_meng/article/details/106261280)
* [[知乎/OLDPAN]扔掉anchor！真正的CenterNet——Objects as Points论文解读](https://zhuanlan.zhihu.com/p/66048276)

* FCOS
* [FCOS:一阶全卷积目标检测](https://zhuanlan.zhihu.com/p/63868458)
* [[论文阅读] FCOS: Fully Convolutional One-Stage Object Detection](https://bbs.huaweicloud.com/blogs/255656)