Abstract

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.

Original languageEnglish (US)
Title of host publication2018 IEEE International Conference on Image Processing, ICIP 2018 - Proceedings
PublisherIEEE Computer Society
Pages3418-3422
Number of pages5
ISBN (Electronic)9781479970612
DOIs
StatePublished - Aug 29 2018
Event25th IEEE International Conference on Image Processing, ICIP 2018 - Athens, Greece
Duration: Oct 7 2018Oct 10 2018

Publication series

NameProceedings - International Conference on Image Processing, ICIP
ISSN (Print)1522-4880

Conference

Conference25th IEEE International Conference on Image Processing, ICIP 2018
CountryGreece
CityAthens
Period10/7/1810/10/18

Fingerprint

Labels
Image classification
Learning algorithms
Problem-Based Learning
Personnel

Keywords

  • CNN
  • Deep Active Learning
  • LSTM

ASJC Scopus subject areas

  • Software
  • Computer Vision and Pattern Recognition
  • Signal Processing

Cite this

Ranganathan, H., Demakethepalli Venkateswara, H., Chakraborty, S., & Panchanathan, S. (2018). Multi-Label Deep Active Learning with Label Correlation. In 2018 IEEE International Conference on Image Processing, ICIP 2018 - Proceedings (pp. 3418-3422). [8451460] (Proceedings - International Conference on Image Processing, ICIP). IEEE Computer Society. https://doi.org/10.1109/ICIP.2018.8451460

Multi-Label Deep Active Learning with Label Correlation. / Ranganathan, Hiranmayi; Demakethepalli Venkateswara, Hemanth; Chakraborty, Shayok; Panchanathan, Sethuraman.

2018 IEEE International Conference on Image Processing, ICIP 2018 - Proceedings. IEEE Computer Society, 2018. p. 3418-3422 8451460 (Proceedings - International Conference on Image Processing, ICIP).

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Ranganathan, H, Demakethepalli Venkateswara, H, Chakraborty, S & Panchanathan, S 2018, Multi-Label Deep Active Learning with Label Correlation. in 2018 IEEE International Conference on Image Processing, ICIP 2018 - Proceedings., 8451460, Proceedings - International Conference on Image Processing, ICIP, IEEE Computer Society, pp. 3418-3422, 25th IEEE International Conference on Image Processing, ICIP 2018, Athens, Greece, 10/7/18. https://doi.org/10.1109/ICIP.2018.8451460
Ranganathan H, Demakethepalli Venkateswara H, Chakraborty S, Panchanathan S. Multi-Label Deep Active Learning with Label Correlation. In 2018 IEEE International Conference on Image Processing, ICIP 2018 - Proceedings. IEEE Computer Society. 2018. p. 3418-3422. 8451460. (Proceedings - International Conference on Image Processing, ICIP). https://doi.org/10.1109/ICIP.2018.8451460
Ranganathan, Hiranmayi ; Demakethepalli Venkateswara, Hemanth ; Chakraborty, Shayok ; Panchanathan, Sethuraman. / Multi-Label Deep Active Learning with Label Correlation. 2018 IEEE International Conference on Image Processing, ICIP 2018 - Proceedings. IEEE Computer Society, 2018. pp. 3418-3422 (Proceedings - International Conference on Image Processing, ICIP).
@inproceedings{20320cf256c948a5a74464294f22fac5,
title = "Multi-Label Deep Active Learning with Label Correlation",
abstract = "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.",
keywords = "CNN, Deep Active Learning, LSTM",
author = "Hiranmayi Ranganathan and {Demakethepalli Venkateswara}, Hemanth and Shayok Chakraborty and Sethuraman Panchanathan",
year = "2018",
month = "8",
day = "29",
doi = "10.1109/ICIP.2018.8451460",
language = "English (US)",
series = "Proceedings - International Conference on Image Processing, ICIP",
publisher = "IEEE Computer Society",
pages = "3418--3422",
booktitle = "2018 IEEE International Conference on Image Processing, ICIP 2018 - Proceedings",

}

TY - GEN

T1 - Multi-Label Deep Active Learning with Label Correlation

AU - Ranganathan, Hiranmayi

AU - Demakethepalli Venkateswara, Hemanth

AU - Chakraborty, Shayok

AU - Panchanathan, Sethuraman

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

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

ER -