Abstract
Recent successes on face recognition tasks require a large number of annotated samples for training models. However, the sample-labeling process is slow and expensive. An effective approach to reduce the annotation effort is active learning (AL). However, the traditional AL methods are limited by the hand-craft features and the small-scale datasets. In this paper, we propose a novel deep active learning framework combining the optimal feature representation of deep convolutional neural network (CNN) and labeling-cost saving of AL, which jointly learns feature and recognition model from unlabeled samples with minimal annotation cost. The model is initialized by a relative small number of labeled samples, and strengthened gradually by adding much more complementary samples for retraining in a progressive way. Our method takes both high-uncertainty samples and the high-confidence samples into consideration for the stability of model. Specifically, the high-confidence samples are selected in a self-paced learning way, and they are double verified by the prior knowledge for more reliable. These high-confidence samples are labeled by estimated class directly, and our framework jointly learns features and recognition model by combining AL with deep CNN, so we name our approach as heuristic deep active learning (HDAL). We apply HDAL on face recognition task, it achieves our goal of “minimizing the annotation cost while avoiding the performance degradation”, and the experimental results on Cross-Age Celebrity Dataset (CACD) show that the HDAL outperforms other state-of-the-art approaches in both recognition accuracy and annotation cost.
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsNotes
References
Bengio, Y., Louradour, J., Collobert, R., Weston, J.: Curriculum learning. In: ICML, pp. 41–48. ACM (2009)
Kumar, M.P., Packer, B., Koller, D.: Self-paced learning for latent variable models. In: NIPS, pp. 1189–1197 (2010)
Jiang, L., Meng, D., Mitamura, T., Hauptmann, A.G.: Easy samples first: self-paced reranking for zero-example multimedia search. In: MM, pp. 547–556. ACM (2014)
Jiang, L., Meng, D., Zhao, Q., Shan, S., Hauptmann, A.G.: Selfpaced curriculum learning. In: AAAI, pp. 2694–2700. AAAI Press (2015)
Chen, B.-C., Chen, C.-S., Hsu, W.H.: Cross-age reference coding for age-invariant face recognition and retrieval. In: Fleet, D., Pajdla, T., Schiele, B., Tuytelaars, T. (eds.) ECCV 2014. LNCS, vol. 8694, pp. 768–783. Springer, Cham (2014). doi:10.1007/978-3-319-10599-4_49
Lewis, D.D.: A sequential algorithm for training text classifiers: corrigendum and additional data. In: ACM SIGIR Forum, pp. 13–19. ACM (1995)
Joshi, A.J., Porikli, F., Papanikolopoulos, N.: Multi-class active learning for image classification. In: CVPR, pp. 2372–2379. IEEE (2009)
Freund, Y., Seung, H.S., Shamir, E., Tishby, N.: Selective sampling using the query by committee algorithm. Mach. Learn. 133–168 (1997)
McCallumzy, A.K., Nigamy, K.: Employing em and pool-based active learning for text classification. In: ICML, pp. 359–367. Citeseer (1998)
Tong, S., Koller, D.: Support vector machine active learning with applications to text classification. J. Mach. Learn. Res. 45–66 (2002)
Settles, B., Craven, M.: An analysis of active learning strategies for sequence labeling tasks. In: Empirical Methods in Natural Language Processing, pp. 1070–1079. Association for Computational Linguistics (2008)
Li, X., Guo, Y.: Adaptive active learning for image classification. In: CVPR, pp. 859–866. IEEE (2013)
Demir, B., Bruzzone, L.: A novel active learning method in relevance feedback for content-based remote sensing image retrieval. IEEE Trans. Geosci. Remote Sens. 2323–2334 (2015)
Brinker, K.: Incorporating diversity in active learning with support vector machines. In: ICML, pp. 59–66 (2003)
Elhamifar, E., Sapiro, G., Yang, A., Sasrty, S.S.: A convex optimization framework for active learning. In: ICCV, pp. 209–216 (2013)
Jia, Y., Shelhamer, E., Donahue, J., Karayev, S., Long, J., Girshick, R., Guadarrama, S., Darrell, T.: Caffe: convolutional architecture for fast feature embedding. In: MM, pp. 675–678. ACM (2014)
Sun, Y., Wang, X., Tang, X.: Deep convolutional network cascade for facial point detection. In: CVPR, pp. 3476–3483. IEEE (2013)
Acknowledgments
This research is supported by the Research Project of Guangzhou Municipal Universities (No. 1201620302), National Undergraduate Scientific and Technological Innovation Project (No. 201711078017), the Science and Technology Planning Project of Guangdong Province (Nos. 2015B010128009, 2013B010406005). The authors would like to thank the reviewers for their comments and suggestions.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2017 Springer International Publishing AG
About this paper
Cite this paper
Li, Y., Wang, K., Nie, L., Wang, Q. (2017). Face Recognition via Heuristic Deep Active Learning. In: Zhou, J., et al. Biometric Recognition. CCBR 2017. Lecture Notes in Computer Science(), vol 10568. Springer, Cham. https://doi.org/10.1007/978-3-319-69923-3_11
Download citation
DOI: https://doi.org/10.1007/978-3-319-69923-3_11
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-69922-6
Online ISBN: 978-3-319-69923-3
eBook Packages: Computer ScienceComputer Science (R0)