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

Content Provider	IEEE Xplore Digital Library
Author	Heng Yang Patras, I.
Copyright Year	2015
Description	Author affiliation: Queen Mary Univ. of London, London, UK (Heng Yang; Patras, I.)
Abstract	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) 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.
Starting Page	4685
Ending Page	4693
File Size	3031536
Page Count	9
File Format	PDF
ISSN	10636919
e-ISBN	9781467369640
DOI	10.1109/CVPR.2015.7299100
Language	English
Publisher	Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Publisher Date	2015-06-07
Publisher Place	USA
Access Restriction	Subscribed
Rights Holder	Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Subject Keyword	Hip Joints
Content Type	Text
Resource Type	Article
Subject	Computer Vision and Pattern Recognition Software

Sl.	Authority	Responsibilities	Communication Details
1	Ministry of Education (GoI), Department of Higher Education	Sanctioning Authority	https://www.education.gov.in/ict-initiatives
2	Indian Institute of Technology Kharagpur	Host Institute of the Project: The host institute of the project is responsible for providing infrastructure support and hosting the project	https://www.iitkgp.ac.in
3	National Digital Library of India Office, Indian Institute of Technology Kharagpur	The administrative and infrastructural headquarters of the project	Dr. B. Sutradhar bsutra@ndl.gov.in
4	Project PI / Joint PI	Principal Investigator and Joint Principal Investigators of the project	Dr. B. Sutradhar bsutra@ndl.gov.in Prof. Saswat Chakrabarti will be added soon
5	Website/Portal (Helpdesk)	Queries regarding NDLI and its services	support@ndl.gov.in
6	Contents and Copyright Issues	Queries related to content curation and copyright issues	content@ndl.gov.in
7	National Digital Library of India Club (NDLI Club)	Queries related to NDLI Club formation, support, user awareness program, seminar/symposium, collaboration, social media, promotion, and outreach	clubsupport@ndl.gov.in
8	Digital Preservation Centre (DPC)	Assistance with digitizing and archiving copyright-free printed books	dpc@ndl.gov.in
9	IDR Setup or Support	Queries related to establishment and support of Institutional Digital Repository (IDR) and IDR workshops	idr@ndl.gov.in

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

Small-variance nonparametric clustering on the hypersphere

HAMR3: An autonomous 1.7g ambulatory robot

Reinforcement learning of single legged locomotion

Tell me what this is: Few-Shot Incremental Object Learning by a Robot

Pattern recognition with new class discovery

Exoskeleton robot control based on cane and body joint synergies

Tell me what you see: A zero-shot action recognition method based on natural language descriptions

Preloaded hopping with linear multi-modal actuation

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

Similar Documents

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

Small-variance nonparametric clustering on the hypersphere

HAMR3: An autonomous 1.7g ambulatory robot

Reinforcement learning of single legged locomotion

Tell me what this is: Few-Shot Incremental Object Learning by a Robot

Pattern recognition with new class discovery

Exoskeleton robot control based on cane and body joint synergies

Tell me what you see: A zero-shot action recognition method based on natural language descriptions

Preloaded hopping with linear multi-modal actuation

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