Conditional graphical lasso for multi-label image classification
Conference paper
Li, Qiang, Qiao, Maoying, Bian, Wei and Tao, Dacheng. (2016). Conditional graphical lasso for multi-label image classification. 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). Las Vegas, Nevada, United States of America 27 - 30 Jun 2016 Computer Vision Foundation. pp. 2977-2986 https://doi.org/10.1109/CVPR.2016.325
Authors | Li, Qiang, Qiao, Maoying, Bian, Wei and Tao, Dacheng |
---|---|
Type | Conference paper |
Abstract | Multi-label image classification aims to predict multiple labels for a single image which contains diverse content. By utilizing label correlations, various techniques have been developed to improve classification performance. However, current existing methods either neglect image features when exploiting label correlations or lack the ability to learn image-dependent conditional label structures. In this paper, we develop conditional graphical Lasso (CGL) to handle these challenges. CGL provides a unified Bayesian framework for structure and parameter learning conditioned on image features. We formulate the multi-label prediction as CGL inference problem, which is solved by a mean field variational approach. Meanwhile, CGL learning is efficient due to a tailored proximal gradient procedure by applying the maximum a posterior (MAP) methodology. CGL performs competitively for multi-label image classification on benchmark datasets MULAN scene, PASCAL VOC 2007 and PASCAL VOC 2012, compared with the state-of-the-art multi-label classification algorithms. |
Year | 2016 |
Publisher | Computer Vision Foundation |
ISSN | 1063-6919 |
Digital Object Identifier (DOI) | https://doi.org/10.1109/CVPR.2016.325 |
Open access | Open access |
Publisher's version | License All rights reserved File Access Level Open |
Page range | 2977-2986 |
Web address (URL) of conference proceedings | https://doi.org/10.1109/CVPR33180.2016 |
Funder | Australian Research Council (ARC) |
Output status | Published |
Publication process dates | |
Deposited | 19 May 2021 |
ARC Funded Research | This output has been funded, wholly or partially, under the Australian Research Council Act 2001 |
Grant ID | ARC/DP140102164 |
ARC/FT130101457 | |
ARC/LE140100061 |
https://acuresearchbank.acu.edu.au/item/8w16y/conditional-graphical-lasso-for-multi-label-image-classification
Download files
Publisher's version
OA_Li_2016_Conditional_graphical_lasso_for_multi_label.pdf | |
License: All rights reserved | |
File access level: Open |
85
total views44
total downloads3
views this month0
downloads this month