RCNN-→SPP Net-→ Fast RCNN-→ Faster RCNN-→ YOLO-→ SSD

思路是：a,生成候選框 b，CNN提取特征 c,分類網(wǎng)絡(luò) d,回歸，位置精修(refine)

RCNN:

論文:

https://arxiv.org/pdf/1311.2524.pdf

源碼:

https://github.com/rbgirshick/rcnn

一些解讀：

https://blog.csdn.net/shenxiaolu1984/article/details/51066975

https://blog.csdn.net/hjimce/article/details/50187029

https://blog.csdn.net/tsq292978891/article/details/78722813

SPP Net:

論文:

https://arxiv.org/pdf/1406.4729.pdf

源碼:

caffe spp layer:https://blog.csdn.net/u013010889/article/details/53928363

一些解讀:

https://zhuanlan.zhihu.com/p/27485018

Fast RCNN

論文:

https://arxiv.org/pdf/1504.08083.pdf

源碼:

https://github.com/rbgirshick/fast-rcnn

一些解讀:

https://blog.csdn.net/shenxiaolu1984/article/details/51036677

Faster RCNN

論文:

https://arxiv.org/pdf/1506.01497.pdf

源碼:

https://github.com/rbgirshick/py-faster-rcnn

一些解讀:

https://blog.csdn.net/shenxiaolu1984/article/details/51152614

https://blog.csdn.net/u013010889/article/details/78574879

https://zhuanlan.zhihu.com/p/31426458

YOLO/YOLO.V2

論文:

https://www.cv-foundation.org/openaccess/content_cvpr_2016/papers/Redmon_You_Only_Look_CVPR_2016_paper.pdf

https://arxiv.org/pdf/1612.08242.pdf

源碼:

https://github.com/pjreddie/darknet?

一些解讀:

https://blog.csdn.net/ben_ben_niao/article/details/52014285

https://blog.csdn.net/u014380165/article/details/72616238

https://blog.csdn.net/jesse_mx/article/details/53925356

SSD

論文:

https://arxiv.org/abs/1512.02325

源碼:

https://github.com/weiliu89/caffe/tree/ssd

一些解讀:

https://www.cnblogs.com/fariver/p/7347197.html

整個系列總結(jié):

https://blog.csdn.net/linolzhang/article/details/54344350

https://wenku.baidu.com/view/cb977f29f68a6529647d27284b73f242336c31df.html

?

?

?

?

?

?

轉(zhuǎn)載于:https://www.cnblogs.com/buyizhiyou/p/8651790.html

總結(jié)

以上是生活随笔為你收集整理的深度学习目标检测算法综述(论文和代码)的全部內(nèi)容，希望文章能夠幫你解決所遇到的問題。

如果覺得生活随笔網(wǎng)站內(nèi)容還不錯，歡迎將生活随笔推薦給好友。