Mirror, mirror on the wall, tell me, is the error small?

by   Heng Yang, et al.
Queen Mary University of London

Do object part localization methods produce bilaterally symmetric results on mirror images? Surprisingly not, even though state of the art methods augment the training set with mirrored images. In this paper we take a closer look into this issue. We first introduce the concept of mirrorability as the ability of a model to produce symmetric results in mirrored images and introduce a corresponding measure, namely the mirror error that is defined as the difference between the detection result on an image and the mirror of the detection result on its mirror image. We evaluate the mirrorability of several state of the art algorithms in two of the most intensively studied problems, namely human pose estimation and face alignment. Our experiments lead to several interesting findings: 1) Surprisingly, most of state of the art methods struggle to preserve the mirror symmetry, despite the fact that they do have very similar overall performance on the original and mirror images; 2) the low mirrorability is not caused by training or testing sample bias - all algorithms are trained on both the original images and their mirrored versions; 3) the mirror error is strongly correlated to the localization/alignment error (with correlation coefficients around 0.7). Since the mirror error is calculated without knowledge of the ground truth, we show two interesting applications - in the first it is used to guide the selection of difficult samples and in the second to give feedback in a popular Cascaded Pose Regression method for face alignment.


page 1

page 3

page 4

page 5

page 6


An Iterative Regression Approach for Face Pose Estimation from RGB Images

This paper presents a iterative optimization method, explicit shape regr...

Face Alignment Assisted by Head Pose Estimation

In this paper we propose a supervised initialization scheme for cascaded...

A simple yet effective baseline for 3d human pose estimation

Following the success of deep convolutional networks, state-of-the-art m...

Self-Correctable and Adaptable Inference for Generalizable Human Pose Estimation

A central challenge in human pose estimation, as well as in many other m...

Binarized Convolutional Landmark Localizers for Human Pose Estimation and Face Alignment with Limited Resources

Our goal is to design architectures that retain the groundbreaking perfo...

Graph-PCNN: Two Stage Human Pose Estimation with Graph Pose Refinement

Recently, most of the state-of-the-art human pose estimation methods are...

EGL++: Extending Expected Gradient Length to Active Learning for Human Pose Estimation

State of the art human pose estimation models continue to rely on large ...

Please sign up or login with your details

Forgot password? Click here to reset