short-paper

Weak Labeled Multi-Label Active Learning for Image Classification

Authors:

Shiquan Zhao,

Jian Wu,

Victor S. Sheng,

Chen Ye,

Pengpeng Zhao,

Zhiming CuiAuthors Info & Claims

MM '15: Proceedings of the 23rd ACM international conference on Multimedia

Pages 1127 - 1130

https://doi.org/10.1145/2733373.2806298

Published: 13 October 2015 Publication History

Get Access

Abstract

In order to achieve better classification performance with even fewer labeled images, active learning is suitable for these situations. Several active learning methods have been proposed for multi-label image classification, but all of them assume that all training images with complete labels. However, as a matter of fact, it is very difficult to get complete labels for each example, especially when the size of labels in a multi-label domain is huge. Usually, only partial labels are available. This is one kind of "weak label" problems. This paper proposes an ingeniously solution to this "weak label" problem on multi-label active learning for image classification (called WLMAL). It explores label correlation on the weak label problem with the help of input features, and then utilizes label correlation to evaluate the informativeness of each example-label pair in a multi-label dataset for active sampling. Our experimental results on three real-world datasets show that our proposed approach WLMAL consistently outperforms existing approaches significantly.

References

[1]

Joshi, A. J., Porikli, F., & Papanikolopoulos, N. Multi-class active learning for image classification. Proceedings of the 22th IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2009, pp. 2372--2379.

Crossref

Google Scholar

[2]

Xu, X. S., Jiang Y., Peng L., Xue X., Zhou Z. H. Ensemble approach based on conditional random field for multi-label image and video annotation. Proceedings of the 19th ACM International Conference on Multimedia (ACM MM), 2011, pp. 1377--1380.

Digital Library

Google Scholar

[3]

Qi, G. J., Hua, X. S., Rui, Y., Tang, J., & Zhang, H. J. Two-dimensional active learning for image classification. Proceedings of the 21th IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2008, pp. 1--8.

Google Scholar

[4]

Wu, J., Sheng V.S., Zhang J., Zhao P. P., Cui Z. M. Multi-label Active Learning for Image Classification. Proceedings of the 18th IEEE International Conference on Image Processing (ICIP), 2014, pp. 5227--5231.

Google Scholar

[5]

Bang Z., Yang W., Fang C. Multilabel image classification via high-order label correlation driven active learning. IEEE Transactions on Image Processing, 2014, 23(3): 1430--1441.

Digital Library

Google Scholar

[6]

Li X., Guo Y. Active learning with multi-label svm classification, Proceedings of the 23th International Joint Conference on Artificial Intelligence (IJCAI), 2013, pp. 1479--1485.

Digital Library

Google Scholar

[7]

Zhang, Y. Multi-Task Active Learning with Output Constraints, Proceedings of the 24th AAAI Conference on Artificial Intelligence (AAAI), 2010, pp. 667--672.

Google Scholar

[8]

Sun, Y. Y., Zhang, Y., Zhou, Z. H. Multi-label learning with weak label. Proceedings of the 24th AAAI Conference on Artificial Intelligence (AAAI), 2010, pp. 593--598.

Google Scholar

[9]

Dembczynski, K., Waegeman, W., Cheng, W., Hüllermeier, E. On label dependence in multi-label classification. Proceedings of the 2nd International Workshop on Learning from Multi-Label Data, 2010, pp. 5--12.

Google Scholar

[10]

Read, J., Pfahringer, B., Holmes, G., Frank, E. Classifier chains for multi-label classification. Machine learning, 2011, 85(3), 333--359.

Digital Library

Google Scholar

[11]

Tsoumakas G, Spyromitros-Xioufis E, Vilcek J, et al. MULAN: A Java Library for Multi-Label Learning{J}. Journal of Machine Learning Research, 2011, 12(7):2411--2414.

Digital Library

Google Scholar

[12]

Spyromitros E., Tsoumakas G., Vlahavas I. An empirical study of lazy multi-label classification algorithms. Artificial Intelligence: Theories, Models and Applications, Springer Berlin Heidelberg, 2008, pp. 401--406.

Digital Library

Google Scholar

Cited By

View all

Goswami DChakraborty S(2024)Active Batch Sampling for Multi-label Classification with Binary User Feedback2024 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)10.1109/WACV57701.2024.00252(2522-2531)Online publication date: 3-Jan-2024
https://doi.org/10.1109/WACV57701.2024.00252
Li WQian WChen LJia X(2024)Sample diversity selection strategy based on label distribution morphology for active label distribution learningPattern Recognition10.1016/j.patcog.2024.110322150(110322)Online publication date: Jun-2024
https://doi.org/10.1016/j.patcog.2024.110322
Chung CLee JPark KLee JKim MSong MKim YChoo JHong S(2021)Understanding Human-side Impact of Sampling Image Batches in Subjective Attribute LabelingProceedings of the ACM on Human-Computer Interaction10.1145/34760375:CSCW2(1-26)Online publication date: 18-Oct-2021
https://dl.acm.org/doi/10.1145/3476037
Show More Cited By

Index Terms

Weak Labeled Multi-Label Active Learning for Image Classification
1. Computing methodologies
  1. Artificial intelligence
    1. Computer vision
      1. Computer vision problems
      2. Computer vision tasks
        Scene understanding

Recommendations

Multi-Label Active Learning with Chi-Square Statistics for Image Classification
ICMR '15: Proceedings of the 5th ACM on International Conference on Multimedia Retrieval

Active learning is to select the most informative examples to request their labels. Most previous studies in active learning for multi-label classification didn't pay enough attention on label correlations. This leads to a bad performance for ...
Adaptive Low-Rank Multi-Label Active Learning for Image Classification
MM '17: Proceedings of the 25th ACM international conference on Multimedia

Multi-label active learning for image classification has attracted great attention over recent years and a lot of relevant works are published continuously. However, there still remain some problems that need to be solved, such as existing multi-label ...
Semi-supervised multi-label classification using incomplete label information
Highlights
- An inductive semi-supervised method called Smile is proposed for multi-label classification using incomplete label information.
Abstract
Classifying multi-label instances using incompletely labeled instances is one of the fundamental tasks in multi-label learning. Most existing methods regard this task as supervised weak-label learning problem and assume sufficient ...

Comments

Information & Contributors

Information

Published In

MM '15: Proceedings of the 23rd ACM international conference on Multimedia

October 2015

1402 pages

ISBN:9781450334594

DOI:10.1145/2733373

General Chairs:
Xiaofang Zhou
The University of Queensland, Australia
,
Alan F. Smeaton
Dublin City University, Ireland
,
Qi Tian
The University of Texas at San Antonio, USA
,
Program Chairs:
Dick C.A. Bulterman
FXPAL, USA
,
Heng Tao Shen
The University of Queensland, Australia
,
Ketan Mayer-Patel
The University of North Carolina, USA
,
Shuicheng Yan
National University of Singapore, Singapore

Permission to make digital or hard copies of all or part of this work for personal or classroom use is granted without fee provided that copies are not made or distributed for profit or commercial advantage and that copies bear this notice and the full citation on the first page. Copyrights for components of this work owned by others than ACM must be honored. Abstracting with credit is permitted. To copy otherwise, or republish, to post on servers or to redistribute to lists, requires prior specific permission and/or a fee. Request permissions from [email protected]

Publisher

Association for Computing Machinery

New York, NY, United States

Publication History

Published: 13 October 2015

Permissions

Request permissions for this article.

Request Permissions

Check for updates

Author Tags

Qualifiers

Short-paper

Funding Sources

Basic Research Program of Jiangsu Education Department
Government of Jiangsu Province
National Science Foundation
National Natural Science Foundation of China

Conference

MM '15

Sponsor:

SIGMM

MM '15: ACM Multimedia Conference

October 26 - 30, 2015

Brisbane, Australia

Acceptance Rates

MM '15 Paper Acceptance Rate 56 of 252 submissions, 22%;

Overall Acceptance Rate 995 of 4,171 submissions, 24%

Upcoming Conference

MM '24

Sponsor:
sigmm

The 32nd ACM International Conference on Multimedia

October 28 - November 1, 2024

Melbourne , VIC , Australia

Contributors

Other Metrics

View Article Metrics

Bibliometrics & Citations

Bibliometrics

Article Metrics

10
Total Citations
View Citations
383
Total Downloads

Downloads (Last 12 months)7
Downloads (Last 6 weeks)0

Reflects downloads up to 30 Aug 2024

Other Metrics

View Author Metrics

Citations

Cited By

View all

Goswami DChakraborty S(2024)Active Batch Sampling for Multi-label Classification with Binary User Feedback2024 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)10.1109/WACV57701.2024.00252(2522-2531)Online publication date: 3-Jan-2024
https://doi.org/10.1109/WACV57701.2024.00252
Li WQian WChen LJia X(2024)Sample diversity selection strategy based on label distribution morphology for active label distribution learningPattern Recognition10.1016/j.patcog.2024.110322150(110322)Online publication date: Jun-2024
https://doi.org/10.1016/j.patcog.2024.110322
Chung CLee JPark KLee JKim MSong MKim YChoo JHong S(2021)Understanding Human-side Impact of Sampling Image Batches in Subjective Attribute LabelingProceedings of the ACM on Human-Computer Interaction10.1145/34760375:CSCW2(1-26)Online publication date: 18-Oct-2021
https://dl.acm.org/doi/10.1145/3476037
Ghajargar MPersson JBardzell JHolmberg LTegen ALamas DSarapuu HŠmorgun IBerget G(2020)The UX of Interactive Machine LearningProceedings of the 11th Nordic Conference on Human-Computer Interaction: Shaping Experiences, Shaping Society10.1145/3419249.3421236(1-3)Online publication date: 25-Oct-2020
https://dl.acm.org/doi/10.1145/3419249.3421236
Wu JSheng VZhang JLi HDadakova TSwisher CCui ZZhao P(2020)Multi-Label Active Learning Algorithms for Image ClassificationACM Computing Surveys10.1145/337950453:2(1-35)Online publication date: 20-Mar-2020
https://dl.acm.org/doi/10.1145/3379504
Gao QTrajcevski GZhou FZhang KZhong TZhang FBanaei-Kashani FHoel EGüting RTamassia RXiong L(2018)Trajectory-based social circle inferenceProceedings of the 26th ACM SIGSPATIAL International Conference on Advances in Geographic Information Systems10.1145/3274895.3274908(369-378)Online publication date: 6-Nov-2018
https://dl.acm.org/doi/10.1145/3274895.3274908
Reyes OVentura S(2018)Evolutionary Strategy to Perform Batch-Mode Active Learning on Multi-Label DataACM Transactions on Intelligent Systems and Technology10.1145/31616069:4(1-26)Online publication date: 30-Jan-2018
https://dl.acm.org/doi/10.1145/3161606
Wu JZhao SSheng VZhang JYe CZhao PCui Z(2017)Weak-Labeled Active Learning With Conditional Label Dependence for Multilabel Image ClassificationIEEE Transactions on Multimedia10.1109/TMM.2017.265206519:6(1156-1169)Online publication date: 1-Jun-2017
https://dl.acm.org/doi/10.1109/TMM.2017.2652065
Wu JYe CSheng VZhang JZhao PCui Z(2017)Active learning with label correlation exploration for multi‐label image classificationIET Computer Vision10.1049/iet-cvi.2016.024311:7(577-584)Online publication date: 21-Aug-2017
https://dl.acm.org/doi/10.1049/iet-cvi.2016.0243
Gao NHuang SChen S(2016)Multi-label active learning by model guided distribution matchingFrontiers of Computer Science: Selected Publications from Chinese Universities10.1007/s11704-016-5421-x10:5(845-855)Online publication date: 1-Oct-2016
https://dl.acm.org/doi/10.1007/s11704-016-5421-x

View Options

Get Access

Login options

Check if you have access through your login credentials or your institution to get full access on this article.

Cited By

Index Terms

Recommendations

Multi-Label Active Learning with Chi-Square Statistics for Image Classification

Adaptive Low-Rank Multi-Label Active Learning for Image Classification

Semi-supervised multi-label classification using incomplete label information