TY - GEN
T1 - Adaptive low-rank multi-label active learning for image classification
AU - Wu, Jian
AU - Guo, Anqian
AU - Sheng, Victor S.
AU - Zhao, Pengpeng
AU - Cui, Zhiming
AU - Li, Hua
N1 - Funding Information:
‘is research was partially supported by the Natural Science Foundation of China under grant No.61402311, Jiangsu Province Colleges and Universities Natural Science Research Project under grant No.13KJB520021, and the U.S. National Science Foundation (IIS-1115417).
Publisher Copyright:
© 2017 ACM.
PY - 2017/10/23
Y1 - 2017/10/23
N2 - 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 active learning algorithms do not reflect on the cleanness of sample data and their ways on label correlation mining are defective. For one thing, sample data is usually contaminated in reality, which disturbs the estimation of data distribution and further hinders the model training. For another, previous approaches for label relationship exploration are purely based on the observed label distribution of an incomplete training set, which cannot provide sufficiently efficient information. To address these issues, we propose a novel adaptive low-rank multi-label active learning algorithm, called LRMAL. Specifically, we first use low-rank matrix recovery to learn an effective low-rank feature representation from the noisy data. In a subsequent sampling phase, we make use of its superiorities to evaluate the general informativeness of each unlabelled example-label pair. Based on an intrinsic mapping relation between the example space and the label space of a certain multi-label dataset, we recover the incomplete labels of a training set for a more comprehensive label correlation mining. Furthermore, to reduce the redundancy among the selected example-label pairs, we use a diversity measurement to diversify the sampled data. Finally, an effective sampling strategy is developed by integrating these two aspects of potential information with uncertainty based on an adaptive integration scheme. Experimental results demonstrate the effectiveness of our approach.
AB - 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 active learning algorithms do not reflect on the cleanness of sample data and their ways on label correlation mining are defective. For one thing, sample data is usually contaminated in reality, which disturbs the estimation of data distribution and further hinders the model training. For another, previous approaches for label relationship exploration are purely based on the observed label distribution of an incomplete training set, which cannot provide sufficiently efficient information. To address these issues, we propose a novel adaptive low-rank multi-label active learning algorithm, called LRMAL. Specifically, we first use low-rank matrix recovery to learn an effective low-rank feature representation from the noisy data. In a subsequent sampling phase, we make use of its superiorities to evaluate the general informativeness of each unlabelled example-label pair. Based on an intrinsic mapping relation between the example space and the label space of a certain multi-label dataset, we recover the incomplete labels of a training set for a more comprehensive label correlation mining. Furthermore, to reduce the redundancy among the selected example-label pairs, we use a diversity measurement to diversify the sampled data. Finally, an effective sampling strategy is developed by integrating these two aspects of potential information with uncertainty based on an adaptive integration scheme. Experimental results demonstrate the effectiveness of our approach.
KW - Active learning
KW - Label correlation
KW - Low-rank representation
KW - Multi-label image classification
UR - http://www.scopus.com/inward/record.url?scp=85035217598&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85035217598&partnerID=8YFLogxK
U2 - 10.1145/3123266.3123388
DO - 10.1145/3123266.3123388
M3 - Conference contribution
AN - SCOPUS:85035217598
T3 - MM 2017 - Proceedings of the 2017 ACM Multimedia Conference
SP - 1336
EP - 1344
BT - MM 2017 - Proceedings of the 2017 ACM Multimedia Conference
PB - Association for Computing Machinery
T2 - 25th ACM International Conference on Multimedia, MM 2017
Y2 - 23 October 2017 through 27 October 2017
ER -