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