TY - GEN
T1 - Multi-Label Deep Active Learning with Label Correlation
AU - Ranganathan, Hiranmayi
AU - Demakethepalli Venkateswara, Hemanth
AU - Chakraborty, Shayok
AU - Panchanathan, Sethuraman
N1 - Publisher Copyright:
© 2018 IEEE.
PY - 2018/8/29
Y1 - 2018/8/29
N2 - Annotating a data sample in a multi-label learning problem requires a human oracle to consider the presence/absence of every possible label separately, which is extremely labor intensive. Active learning algorithms automatically identify the informative samples from large amounts of unlabeled data and significantly reduce human annotation efforts in inducing a classification model. Further, deep models have gained popularity to automatically learn representative features from a given dataset and have depicted promising empirical performance in a variety of applications. In this paper, we exploit the feature learning capabilities of deep neural networks and propose a novel framework to address the problem of multi-label active learning with label correlation. We integrate an active selection criterion to the objective function and train deep networks to optimize the function. Our extensive empirical studies on five benchmark multi-label datasets show that our methods outperform the state-of-the-art algorithms, corroborating their potential for real-world image classification applications.
AB - Annotating a data sample in a multi-label learning problem requires a human oracle to consider the presence/absence of every possible label separately, which is extremely labor intensive. Active learning algorithms automatically identify the informative samples from large amounts of unlabeled data and significantly reduce human annotation efforts in inducing a classification model. Further, deep models have gained popularity to automatically learn representative features from a given dataset and have depicted promising empirical performance in a variety of applications. In this paper, we exploit the feature learning capabilities of deep neural networks and propose a novel framework to address the problem of multi-label active learning with label correlation. We integrate an active selection criterion to the objective function and train deep networks to optimize the function. Our extensive empirical studies on five benchmark multi-label datasets show that our methods outperform the state-of-the-art algorithms, corroborating their potential for real-world image classification applications.
KW - CNN
KW - Deep Active Learning
KW - LSTM
UR - http://www.scopus.com/inward/record.url?scp=85062900786&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85062900786&partnerID=8YFLogxK
U2 - 10.1109/ICIP.2018.8451460
DO - 10.1109/ICIP.2018.8451460
M3 - Conference contribution
AN - SCOPUS:85062900786
T3 - Proceedings - International Conference on Image Processing, ICIP
SP - 3418
EP - 3422
BT - 2018 IEEE International Conference on Image Processing, ICIP 2018 - Proceedings
PB - IEEE Computer Society
T2 - 25th IEEE International Conference on Image Processing, ICIP 2018
Y2 - 7 October 2018 through 10 October 2018
ER -