【论文】【论文】王晓刚老师课题组ICCV2017论文：学习特征金字塔用于人体姿态估计（附代码）

点击上方 “机器学习研究会”可以订阅哦

摘要

 

转自：_胖丁_

论文《Learning Feature Pyramids for Human Pose Estimation》提出一个新的特征金字塔模块, 在卷积网络中学习特征金字塔, 并修正了现有的网络参数初始化方法, 在人体姿态估计和图像分类中都取得了很好的效果.

摘要：

Articulated human pose estimation is a fundamental yet challenging task in computer vision. The difficulty is particularly pronounced in scale variations of human body parts when camera view changes or severe foreshortening happens. Although pyramid methods are widely used to handle scale changes at inference time, learning feature pyramids in deep convolutional neural networks (DCNNs) is still not well explored. In this work, we design a Pyramid Residual Module (PRMs) to enhance the invariance in scales of DCNNs. Given input features, the PRMs learn convolutional filters on various scales of input features, which are obtained with different subsampling ratios in a multi-branch network. Moreover, we observe that it is inappropriate to adopt existing methods to initialize the weights of multi-branch networks, which achieve superior performance than plain networks in many tasks recently. Therefore, we provide theoretic derivation to extend the current weight initialization scheme to multi-branch network structures. We investigate our method on two standard benchmarks for human pose estimation. Our approach obtains state-of-the-art results on both benchmarks. Code is available at this https URL

论文链接：

https://arxiv.org/abs/1708.01101

代码链接：

https://github.com/bearpaw/PyraNet

原文链接：

https://m.weibo.cn/2308679910/4137117037132203

“完整内容”请点击【阅读原文】

↓↓↓