Adaptive Multi-class Correlation Filters

Yang, Linlin, Chen, Chen, Wang, Hainan, Zhang, Baochang and Han, Jungong (2016) Adaptive Multi-class Correlation Filters. In: Advances in Multimedia Information Processing - PCM 2016 :17th Pacific-Rim Conference on Multimedia, Xi´ an, China, September 15-16, 2016. Lecture Notes in Computer Science, 9917 (II). Springer, pp. 680-688. ISBN 978-3-319-48895-0

Full text not available from this repository.
Official URL: http://dx.doi.org/10.1007/978-3-319-48896-7_67

Abstract

Correlation filters have attracted growing attention due to their high efficiency, which have been well studied for binary classification. However, by setting the desired output to be a fixed Gaussian function, the conventional multi-class classification based on correlation filters becomes problematic due to the under-fitting in many real-world applications. In this paper, we propose an adaptive multi-class correlation filters (AMCF) method based on an alternating direction method of multipliers (ADMM) framework. Within this framework, we introduce an adaptive output to alleviate the under-fitting problem in the ADMM iterations. By doing so, a closed-form sub-solution is obtained and further used to constrain the optimization objective, simplifying the entire inference mechanism. The proposed approach is successfully combined with the Histograms of Oriented Gradients (HOG) features, multi-channel features and convolution features, and achieves superior performances over state-of-the-arts in two multi-class classification tasks including handwritten digits recognition and RGBD-based action recognition.

Item Type: Book Section
Uncontrolled Keywords: Multi-class correlation filters, ADMM, Adaptive output
Subjects: G400 Computer Science
Department: Faculties > Engineering and Environment > Computer and Information Sciences
Depositing User: Becky Skoyles
Date Deposited: 09 Jan 2017 14:39
Last Modified: 12 Oct 2019 22:27
URI: http://nrl.northumbria.ac.uk/id/eprint/29065

Actions (login required)

View Item View Item

Downloads

Downloads per month over past year

View more statistics