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

Bulat, Adrian; Tzimiropoulos, Georgios

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, October). Binarized Convolutional Landmark Localizers for Human Pose Estimation and Face Alignment with Limited Resources. Presented at International Conference on Computer Vision (ICCV17), Venice, Italy

• Presentation Conference Type: Edited Proceedings
• Conference Name: International Conference on Computer Vision (ICCV17)
• Start Date: Oct 27, 2017
• End Date: Oct 29, 2017
• Acceptance Date: Jul 17, 2017
• Online Publication Date: Dec 25, 2017
• Publication Date: Dec 22, 2017
• Deposit Date: Aug 9, 2017
• Publicly Available Date: Dec 22, 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: Proceedings - 2017 IEEE International Conference on Computer Vision (ICCV 2017)
• ISBN: 9781538610336
• DOI: https://doi.org/10.1109/ICCV.2017.400
• Public URL: https://nottingham-repository.worktribe.com/output/889913
• Publisher URL: http://ieeexplore.ieee.org/document/8237662/
• Related Public URLs: http://iccv2017.thecvf.com/
• 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
• Contract Date: Aug 9, 2017