[人脸关键点检测] Wing loss

转载请注明作者和出处： http://blog.csdn.net/john_bh/

论文链接:Wing Loss for Robust Facial Landmark Localisation with Convolutional Neural Networks
**作者及团队：萨里大学 & 江南大学 **
会议及时间：CVPR 2018
code:github 地址

文章目录

• 论文解读
• 1.主要贡献
• 2.分析比较L1，L2和smooth L1损失函数
• 3.wing loss
• 4.Pose-based data balancing
• 5.Two-stage landmark localisation
• 论文翻译
• Abstract
• 1.Introduction

论文解读

首先这篇论文是由萨里大学研究人员（第一至四作者）与江南大学研究人员（第五作者）共同研究，被CVPR2018收录。

1.主要贡献

• 基于CNN的基于回归的面部界标定位的不同损失函数的系统分析，从经验和理论上比较L1，L2和平滑L1损失函数，发现L1和平滑L1的性能要比广泛使用的L2损失好得多。对于基于CNN的定位模型的训练，应更加关注中小范围误差;
• 提出了一个新的损失函数Wing loss，旨在提高深度网络训练过程中应对小范围和中等范围内的误差的能力；
• 提出了基于姿态的(pose-based)的数据增量策略，可以补偿训练集中头部外平面旋转较大的样本出现的频率较低，主要解决训练数据平衡性问题；
• 提出一个二阶段的人脸关键点检测网络框架；

2.分析比较L1，L2和smooth L1损失函数

3.wing loss

4.Pose-based data balancing

5.Two-stage landmark localisation

论文翻译

Abstract

We present a new loss function, namely Wing loss, for robust facial landmark localisation with Convolutional Neural Networks (CNNs). We first compare and analyse different loss functions including L2, L1 and smooth L1. The analysis of these loss functions suggests that, for the training of a CNN-based localisation model, more attention should be paid to small and medium range errors. To this end, we design a piece-wise loss function. The new loss amplifies the impact of errors from the interval (-w, w) by switching from L1 loss to a modified logarithm function.
我们提出了一种新的损失函数，即Wing损失，用于通过卷积神经网络（CNN）进行鲁棒的面部界标定位。我们首先比较和分析不同的损失函数，包括L2，L1和平滑L1。对这些损失函数的分析表明，对于基于CNN的定位模型的训练，应更加关注中小范围误差。为此，我们设计了分段损失函数。通过从L1损耗切换到修改的对数函数，新的损耗放大了间隔（-w，w）中误差的影响。

To address the problem of under-representation of samples with large out-of-plane head rotations in the training set, we propose a simple but effective boosting strategy, referred to as pose-based data balancing. In particular, we deal with the data imbalance problem by duplicating the minority training samples and perturbing them by injecting random image rotation, bounding box translation and other data augmentation approaches. Last, the proposed approach is extended to create a two-stage framework for robust facial landmark localisation. The experimental results obtained on AFLW and 300W demonstrate the merits of the Wing loss function, and prove the superiority of the proposed method over the state-of-the-art approaches.
为了解决训练集中头部旋转角度较大的样本的代表性不足的问题，我们提出了一种简单但有效的增强策略，称为基于姿势的数据平衡。特别是，我们通过复制少数训练样本并通过注入随机图像旋转，边界框平移和其他数据增强方法来扰动它们来处理数据不平衡问题。最后，将提出的方法扩展为创建两阶段框架，以实现可靠的面部界标定位。在AFLW和300W上获得的实验结果证明了Wing损失函数的优点，并证明了该方法优于最新方法的优越性。

1.Introduction

• presenting a systematic analysis of different loss functions that could be used for regression-based facial landmark localisation with
  CNNs, which to our best knowledge is the first such study carried out in connection with the landmark localisation problem. We empirically and theoretically compare L1, L2 and smooth L1 loss functions and find that L1 and smooth L1 perform much better than the widely used L2 loss.
• a novel loss function, namely the Wing loss, which is designed to improve the deep neural network training capability for small and
  medium range errors. a data augmentation strategy, i.e.
• pose-based data balancing,that compensates the low frequency of occurrence of samples with large out-of-plane head rotations in the
  training set.
• a two-stage facial landmark localisation framework for performance boosting.
• 提出了可用于基于CNN的基于回归的面部界标定位的不同损失函数的系统分析，据我们所知，这是与界标定位问题相关的首次此类研究。 我们从经验和理论上比较L1，L2和平滑L1损失函数，发现L1和平滑L1的性能要比广泛使用的L2损失好得多。
• 一种新颖的损失函数，即Wing损失，旨在改善针对中小范围误差的深度神经网络训练能力。
• 一种数据增强策略，即基于姿势的数据平衡，可以补偿训练集中头部外平面旋转较大的样本出现的频率较低。
• 一个两阶段的面部标志性本地化框架，以提高性能。