Robust object representation by boosting-like deep learning architecture

Wang, Lei, Zhang, Baochang, Han, Jungong, Shen, Linlin and Qian, Cheng-shan (2016) Robust object representation by boosting-like deep learning architecture. Signal Processing: Image Communication, 47. pp. 490-499. ISSN 0923-5965

[img]
Preview
Text
Robust Object Representation by Boosting-like Deep Learning Architecture.pdf - Accepted Version

Download (1MB) | Preview
Official URL: http://dx.doi.org/10.1016/j.image.2016.06.002

Abstract

This paper presents a new deep learning architecture for robust object representation, aiming at efficiently combining the proposed synchronized multi-stage feature (SMF) and a boosting-like algorithm. The SMF structure can capture a variety of characteristics from the inputting object based on the fusion of the handcraft features and deep learned features. With the proposed boosting-like algorithm, we can obtain more convergence stability on training multi-layer network by using the boosted samples. We show the generalization of our object representation architecture by applying it to undertake various tasks, i.e. pedestrian detection and action recognition. Our approach achieves 15.89% and 3.85% reduction in the average miss rate compared with ACF and JointDeep on the largest Caltech dataset, and acquires competitive results on the MSRAction3D dataset.

Item Type: Article
Uncontrolled Keywords: Boosting; Deep learning; Object representation; Synchronized feature
Subjects: G400 Computer Science
Department: Faculties > Engineering and Environment > Computer and Information Sciences
Depositing User: Becky Skoyles
Date Deposited: 10 Nov 2016 14:40
Last Modified: 01 Aug 2021 03:28
URI: http://nrl.northumbria.ac.uk/id/eprint/28492

Actions (login required)

View Item View Item

Downloads

Downloads per month over past year

View more statistics