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
AuthorsLi, Qiang, Qiao, Maoying, Bian, Wei and Tao, Dacheng
TypeConference paper

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.

PublisherComputer Vision Foundation
Digital Object Identifier (DOI)
Open accessOpen access
Publisher's version
All rights reserved
File Access Level
Page range2977-2986
Web address (URL) of conference proceedings
FunderAustralian Research Council
Output statusPublished
Publication process dates
Deposited19 May 2021
ARC Funded ResearchThis output has been funded, wholly or partially, under the Australian Research Council Act 2001
Grant IDARC/DP140102164
Permalink -

Download files

Publisher's version
License: All rights reserved
File access level: Open

  • 0
    total views
  • 0
    total downloads
  • 0
    views this month
  • 0
    downloads this month
These values are for the period from 19th October 2020, when this repository was created.

Export as

Related outputs

Diversified dictionaries for multi-instance learning
Qiao, Maoying, Liu, Liu, Yu, Jun, Xu, Chang and Tao, Dacheng. (2017) Diversified dictionaries for multi-instance learning. Pattern Recognition. 64, pp. 407-416.
Improving stochastic block models by incorporating power-law degree characteristic
Qiao, Maoying, Yu, Jun, Bian, Wei, Li, Qiang and Tao, Dacheng. (2017) Improving stochastic block models by incorporating power-law degree characteristic. Twenty-Sixth International Joint Conference on Artificial Intelligence (IJCAI-17). Melbourne, Australia 19 - 25 Aug 2017 International Joint Conferences on Artificial Intelligence Organization. pp. 2620-2626