人脸方向学习(十七):Face Detection-论文整理-解读
整理的人脸系列学习经验:包括人脸检测、人脸关键点检测、人脸优选、人脸对齐、人脸特征提取等过程总结,有需要的可以参考,仅供学习,请勿盗用。https://blog.csdn.net/TheDayIn_CSDN/article/details/93199307
思路
整理和复现人脸检测相关论文。
一、人脸检测方法篇
Single-stage Methods
• SSD : a classic and widely used single-stage detector with simple model architecture, proposed in 2015.
• RetinaNet : a high-performance single-stage detector with Focal Loss, proposed in 2017.
• GHM : a gradient harmonizing mechanism to improve single-stage detectors, proposed in 2019.
• FCOS : a fully convolutional anchor-free singlestage detector, proposed in 2019.
• FSAF: a feature selective anchor-free module for single-stage detectors, proposed in 2019.
Two-stage Methods
• Fast R-CNN : a classic object detector which requires pre-computed proposals, proposed in 2015.
• Faster R-CNN : a classic and widely used two stage object detector which can be trained end-to-end, proposed in 2015.
• R-FCN : a fully convolutional object detector with faster speed than Faster R-CNN, proposed in 2016.
• Mask R-CNN : a classic and widely used object detection and instance segmentation method, proposed in 2017.
• Grid R-CNN : a grid guided localization mechanism as an alternative to bounding box regression, proposed in 2018.
• Mask Scoring R-CNN : an improvement over Mask R-CNN by predicting the mask IoU, proposed in 2019.
• Double-Head R-CNN : different heads for classi-fification and localization, proposed in 2019.
Multi-stage Methods
• Cascade R-CNN : a powerful multi-stage object detection method, proposed in 2017.
• Hybrid Task Cascade : a multi-stage multi-branch object detection and instance segmentation method, proposed in 2019
. General Modules and Methods
• Mixed Precision Training : train deep neural networks using half precision flfloating point (FP16) numbers, proposed in 2018.
• Soft NMS : an alternative to NMS, proposed in 2017.
• OHEM : an online sampling method that mines hard samples for training, proposed in 2016.
• DCN : deformable convolution and deformable RoI pooling, proposed in 2017.
• DCNv2 : modulated deformable operators, proposed in 2018.
• Train from Scratch : training from random initialization instead of ImageNet pretraining, proposed in 2018.
• ScratchDet : another exploration on training from scratch, proposed in 2018.
• M2Det : a new feature pyramid network to construct more effective feature pyramids, proposed in 2018.
• GCNet : global context block that can effificiently model the global context, proposed in 2019.
• Generalized Attention : a generalized attention formulation, proposed in 2019.
• SyncBN : synchronized batch normalization across GPUs, we adopt the offificial implementation by PyTorch.
• Group Normalization : a simple alternative to BN, proposed in 2018.
• Weight Standardization : standardizing the weights in the convolutional layers for micro-batch training, proposed in 2019.
• HRNet : a new backbone with a focus on learning reliable high-resolution representations, proposed in 2019.
• Guided Anchoring : a new anchoring scheme that predicts sparse and arbitrary-shaped anchors, proposed in 2019.
• Libra R-CNN : a new framework towards balanced learning for object detection, proposed in 2019.
二、人脸检测论文篇
1、caffe-ssd:https://github.com/weiliu89/caffe/tree/ssd
2、Tiny-DSOD:https://github.com/lyxok1/Tiny-DSOD
3、Faster R-CNN:https://arxiv.org/pdf/1506.01497.pdf
4、Fast R-CNN:https://www.cv-foundation.org/openaccess/content_iccv_2015/papers/Girshick_Fast_R-CNN_ICCV_2015_paper.pdf
5、R-FCN:https://arxiv.org/pdf/1605.06409.pdf
人脸方向学习(十七):Face Detection-论文整理-解读相关推荐
- 人脸方向学习(二十):Face Landmark Detection-TS3-解读
最近刷到CVPR和ICCV近两年来在关键点方面的论文,简单总结下,主要是想选一些在移动端能部署的网络结构.最近两年的关键点论文主要用一些主流的方法去做的,比如用教师模型去筛选检测之后的关键点(知识蒸馏 ...
- 人脸方向学习(十六):Face Detection-BlazeFace解读
整理的人脸系列学习经验:包括人脸检测.人脸关键点检测.人脸优选.人脸对齐.人脸特征提取等过程总结,有需要的可以参考,仅供学习,请勿盗用.https://blog.csdn.net/TheDayIn_C ...
- 人脸方向学习(十五):Face Detection-RetinaFace解读
整理的人脸系列学习经验:包括人脸检测.人脸关键点检测.人脸优选.人脸对齐.人脸特征提取等过程总结,有需要的可以参考,仅供学习,请勿盗用.https://blog.csdn.net/TheDayIn_C ...
- 人脸方向学习(十二):Face Detection-Tiny-DSOD解读
整理的人脸系列学习经验:包括人脸检测.人脸关键点检测.人脸优选.人脸对齐.人脸特征提取等过程总结,有需要的可以参考,仅供学习,请勿盗用.https://blog.csdn.net/TheDayIn_C ...
- 人脸方向学习(十一):Face Landmark Detection-PFLD解读
整理的人脸系列学习经验:包括人脸检测.人脸关键点检测.人脸优选.人脸对齐.人脸特征提取五个过程总结,有需要的可以参考,仅供学习,请勿盗用.https://blog.csdn.net/TheDayIn_ ...
- 人脸方向学习(十):Face Detection-MobileNet_SSD解读
整理的人脸系列学习经验:包括人脸检测.人脸关键点检测.人脸优选.人脸对齐.人脸特征提取五个过程总结,有需要的可以参考,仅供学习,请勿盗用.https://blog.csdn.net/TheDayIn_ ...
- 人脸方向学习(九):Face Detection-MTCNN解读
整理的人脸系列学习经验:包括人脸检测.人脸关键点检测.人脸优选.人脸对齐.人脸特征提取等过程总结,有需要的可以参考,仅供学习,请勿盗用.https://blog.csdn.net/TheDayIn_C ...
- 人脸方向学习(八):Face Recognition-MobileFaceNets解读
整理的人脸系列学习经验:包括人脸检测.人脸关键点检测.人脸优选.人脸对齐.人脸特征提取等过程总结,有需要的可以参考,仅供学习,请勿盗用.https://blog.csdn.net/TheDayIn_C ...
- 人脸方向学习(七):Face Recognition-CosFace 解读
整理的人脸系列学习经验:包括人脸检测.人脸关键点检测.人脸优选.人脸对齐.人脸特征提取五个过程总结,有需要的可以参考,仅供学习,请勿盗用.https://blog.csdn.net/TheDayIn_ ...
最新文章
- MVC 4.0 Razor模板引擎 @Html.RenderPartial 与 @Html.RenderAction 区别
- REDHAT6.4桌面环境添加快捷建打开命令行终端
- java与java ee_RxJava + Java8 + Java EE 7 + Arquillian =幸福
- DataNucleus 3.0与Hibernate 3.5
- 【渝粤教育】 国家开放大学2020年春季 1325妇产科学与儿科护理学 参考试题
- python视频教程全集-Python 3视频教程全集(2018版)免费送啦
- 解决tomcat 的端口被占用问题
- npm安装vue-cli时速度慢,fetchMetadata经常卡住并报异常
- 磁力计校正和数据处理
- 49 张图详解 WiFi 的 26 个知识点
- python实现调用百度图像识别api得到图片识别与检测类别和详细信息以及相关准确度
- 阿里巴巴前端实习面经总结(可内推)
- 约分最简分式(python)
- 网吧服务器系统机房图片,很多网吧看不到主机的秘密
- 8月第4周基金排行榜 | TokenInsight
- 苹果iPhone手机怎么恢复备份?详细iOS备份怎么恢复教程
- 学生选课系统业务需求
- 李德毅:希望智能驾驶成为我国继高铁之后又一张新名片
- Js获取字符串asc码
- 数学建模学习笔记(2.3)lingo软件求解线性规划问题
热门文章
- windows phone开发环境搭建
- 校内网脱胎“人人”能成大器
- c++时间片轮转rr进程调度算法_「学习笔记」时间片轮转(RR)调度算法(详解版)...
- Word2Vec算法详解(CBOW和skip-gram算法详解)
- linux vi 内存,Vi Linux内存 之 Slub分配器(四)
- python千行代码项目_p2:千行代码入门python
- 和平精英体验服服务器更新维护什么意思,和平精英8月9日体验服官方申请地址 和平精英更新6项内容需要多注意!和平精英8月9日更新时间确定...
- C语言累加函数代码,ARM汇编程序---通过ARM汇编调用C语言函数实现累加
- python如何对excel排序_Python操作Excel之分组排序
- python 打印的异常回溯和代码不对应