Cost-Effective Active Learning for Deep Image Classification
Top Cited Papers
- 11 July 2016
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Circuits and Systems for Video Technology
- Vol. 27 (12), 2591-2600
- https://doi.org/10.1109/tcsvt.2016.2589879
Abstract
Recent successes in learning-based image classification, however, heavily rely on the large number of annotated training samples, which may require considerable human effort. In this paper, we propose a novel active learning (AL) framework, which is capable of building a competitive classifier with optimal feature representation via a limited amount of labeled training instances in an incremental learning manner. Our approach advances the existing AL methods in two aspects. First, we incorporate deep convolutional neural networks into AL. Through the properly designed framework, the feature representation and the classifier can be simultaneously updated with progressively annotated informative samples. Second, we present a cost-effective sample selection strategy to improve the classification performance with less manual annotations. Unlike traditional methods focusing on only the uncertain samples of low prediction confidence, we especially discover the large amount of high-confidence samples from the unlabeled set for feature learning. Specifically, these high-confidence samples are automatically selected and iteratively assigned pseudolabels. We thus call our framework cost-effective AL (CEAL) standing for the two advantages. Extensive experiments demonstrate that the proposed CEAL framework can achieve promising results on two challenging image classification data sets, i.e., face recognition on the cross-age celebrity face recognition data set database and object categorization on Caltech-256.Keywords
Funding Information
- National Natural Science Foundation of China (61622214)
- State Key Development Program (2016YFB1001000)
- CCF-Tencent Open Fund
- Special Program through the Applied Research on Super Computation of the Natural Science Foundation of China–Guangdong Joint Fund (the second phase)
- NVIDIA Corporation through the Tesla K40 GPU
This publication has 26 references indexed in Scilit:
- ImageNet Large Scale Visual Recognition ChallengeInternational Journal of Computer Vision, 2015
- Robust Multi-label Image Classification with Semi-Supervised Learning and Active LearningLecture Notes in Computer Science, 2015
- Active Learning for Ranking through Expected Loss OptimizationIEEE Transactions on Knowledge and Data Engineering, 2014
- A Novel Active Learning Method in Relevance Feedback for Content-Based Remote Sensing Image RetrievalIEEE Transactions on Geoscience and Remote Sensing, 2014
- Multilabel Image Classification Via High-Order Label Correlation Driven Active LearningIEEE Transactions on Image Processing, 2014
- Extreme video retrievalPublished by Association for Computing Machinery (ACM) ,2006
- Batch mode active learning and its application to medical image classificationPublished by Association for Computing Machinery (ACM) ,2006
- Active Hidden Markov Models for Information ExtractionLecture Notes in Computer Science, 2001
- A mathematical theory of communicationACM SIGMOBILE Mobile Computing and Communications Review, 2001
- A sequential algorithm for training text classifiersACM SIGIR Forum, 1995