Skip to main content

Research Repository

Advanced Search

Binarized convolutional landmark localizers for human pose estimation and face alignment with limited resources

Bulat, Adrian; Tzimiropoulos, Georgios

Authors

Adrian Bulat adrian.bulat@nottingham.ac.uk

Georgios Tzimiropoulos yorgos.tzimiropoulos@nottingham.ac.uk



Abstract

Our goal is to design architectures that retain the groundbreaking performance of CNNs for landmark localization and at the same time are lightweight, compact and suitable for applications with limited computational resources. To this end, we make the following contributions: (a) we are the first to study the effect of neural network binarization on localization tasks, namely human pose estimation and face alignment. We exhaustively evaluate various design choices, identify performance bottlenecks, and more importantly propose multiple orthogonal ways to boost performance. (b) Based on our analysis, we propose a novel hierarchical, parallel and multi-scale residual architecture that yields large performance improvement over the standard bottleneck block while having the same number of parameters, thus bridging the gap between the original network and its binarized counterpart. (c) We perform a large number of ablation studies that shed light on the properties and the performance of the proposed block. (d) We present results for experiments on the most challenging datasets for human pose estimation and face alignment, reporting in many cases state-of-the-art performance. Code can be downloaded from https://www. adrianbulat.com/binary-cnn-landmarks

Citation

Bulat, A., & Tzimiropoulos, G. (2017). Binarized convolutional landmark localizers for human pose estimation and face alignment with limited resources. In 2017 IEEE International Conference on Computer Vision (ICCV 2017). , (3726 - 3734). https://doi.org/10.1109/ICCV.2017.400

Conference Name International Conference on Computer Vision (ICCV17)
Conference Location Venice, Italy
Start Date Oct 27, 2017
End Date Oct 29, 2017
Acceptance Date Jul 17, 2017
Online Publication Date Oct 25, 2017
Publication Date Oct 26, 2017
Deposit Date Aug 9, 2017
Publicly Available Date Oct 25, 2017
Publisher Institute of Electrical and Electronics Engineers
Peer Reviewed Peer Reviewed
Pages 3726 - 3734
Series Title Proceedings (IEEE International Conference on Computer Vision)
Series ISSN 2380-7504
Book Title 2017 IEEE International Conference on Computer Vision (ICCV 2017)
ISBN 9781538610336
DOI https://doi.org/10.1109/ICCV.2017.400
Public URL http://eprints.nottingham.ac.uk/id/eprint/44753
Publisher URL http://ieeexplore.ieee.org/document/8237662/
Related Public URLs http://iccv2017.thecvf.com/
Copyright Statement Copyright information regarding this work can be found at the following address: http://eprints.nottingham.ac.uk/end_user_agreement.pdf
Additional Information © 2017 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works. Published in 2017 IEEE International Conference
on Computer Vision ISBN 9781538610329

Files


0531-3.pdf (1.9 Mb)
PDF

Copyright Statement
Copyright information regarding this work can be found at the following address: http://eprints.nottingham.ac.uk/end_user_agreement.pdf





You might also like



Downloadable Citations