Abstract
Convolutional neural networks (CNNs) have shown significant advantages in computer vision fields. For the optimizations of CNNs, most research works focus on feature extraction, which creates deeper structures and better activations, but the optimizations on dataset is rarely discussed. Due to the boom of data, most CNNs suffer from serious problems of dataset redundancy and following high computational burden. To this end, this paper brings in an informativeness ranking thought and proposes a new methodology for dataset refinement based on Active Learning. Extensive experiments prove its effectiveness to achieve a higher classification accuracy for CNNs at a less training cost. Moreover, for classification problems with a large number of class, this paper further proposes Entropy Ranking, a new Active Learning method, to enhance the optimization ability.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
References
Sun, Y., Chen, Y., Wang, X., Tang, X.: Deep learning face representation by joint identification-verification. In: Advances in neural information processing systems, pp. 1988–1996 (2014)
Huang, F.J., LeCun, Y.: Large-scale learning with SVM and convolutional for generic object categorization. In: 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, vol. 1, pp. 284–291. IEEE (2006)
Zhou, H., Huang, G.B., Lin, Z., Wang, H., Soh, Y.C.: Stacked extreme learning machines. IEEE Trans. Cybern. 45(9), 2013–2025 (2015)
Zhang, L., Chen, C., Bu, J., Cai, D., He, X., Huang, T.S.: Active learning based on locally linear reconstruction. IEEE Trans. Pattern Anal. Mach. Intell. 33(10), 2026–2038 (2011)
Garcia-Pedrajas, N., Perez-Rodriguez, J., de Haro-Garcia, A.: OligoIS: scalable instance selection for class-imbalanced data sets. IEEE Trans. Cybern. 43(1), 332–346 (2013)
Liu, P., Zhang, H., Eom, K.B.: Active deep learning for classification of hyperspectral images. IEEE J. Sel. Top. Appl. Earth Obs. Remote. Sens. 10(2), 712–724 (2017)
Du, B., et al.: Exploring representativeness and informativeness for active learning. IEEE Trans. Cybern. 47(1), 14–26 (2017)
Tuia, D., Pasolli, E., Emery, W.J.: Using active learning to adapt remote sensing image classifiers. Remote Sens. Environ. 115(9), 2232–2242 (2011)
Krizhevsky, A., Hinton, G.: Learning multiple layers of features from tiny images (2009)
Arel, I., Rose, D.C., Karnowski, T.P.: Deep machine learning-a new frontier in artificial intelligence research [research frontier]. IEEE Comput. Intell. Mag. 5(4), 13–18 (2010)
Wen, Y., Zhang, K., Li, Z., Qiao, Yu.: A discriminative feature learning approach for deep face recognition. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9911, pp. 499–515. Springer, Cham (2016). https://doi.org/10.1007/978-3-319-46478-7_31
He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 770–778 (2016)
Szegedy, C., et al.: Going deeper with convolutions. In: Computer Vision and Pattern Recognition, CVPR, pp 1–9 (2015)
Nair, V., Hinton, G.E.: Rectified linear units improve restricted Boltzmann machines. In: Proceedings of the 27th International Conference on Machine Learning, ICML 2010, pp. 807–814 (2010)
He, K., Zhang, X., Ren, S., Sun, J.: Delving deep into rectifiers: surpassing human-level performance on imagenet classification. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 1026–1034 (2015)
Liu, W., Wen, Y., Yu, Z., Yang, M.: Large-margin softmax loss for convolutional neural networks. In: International Conference on Machine Learning, ICML, pp. 507–516 (2016)
Pasolli, E., Melgani, F., Tuia, D., Pacifici, F., Emery, W.J.: Improving active learning methods using spatial information. In: 2011 IEEE International on Geoscience and Remote Sensing Symposium, IGARSS, pp. 3923–3926. IEEE (2011)
Li, M., Sethi, I.K.: Confidence-based active learning. IEEE Trans. Pattern Anal. Mach. Intell. 28(8), 1251–1261 (2006)
Tuia, D., Ratle, F., Pacifici, F., Kanevski, M.F., Emery, W.J.: Active learning methods for remote sensing image classification. IEEE Trans. Geosci. Remote Sens. 47(7), 2218–2232 (2009)
Crawford, M.M., Tuia, D., Yang, H.L.: Active learning: any value for classification of remotely sensed data? Proc. IEEE 101(3), 593–608 (2013)
Jia, Y., et al.: Caffe: convolutional architecture for fast feature embedding. In: Proceedings of the 22nd ACM International Conference on Multimedia, pp. 675–678. ACM (2014)
Acknowledgments
The research was supported by National Natural Science Foundation of China (61671332, U1736206, 41771452, 41771454), Hubei Province Technological Innovation Major Project (2017AAA123) and the National Key Research and Development Program of China (2016YFE0202300).
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2018 Springer Nature Switzerland AG
About this paper
Cite this paper
Liu, S., Zhu, R., Luo, Y., Wang, Z., Zhou, L. (2018). Dataset Refinement for Convolutional Neural Networks via Active Learning. In: Hong, R., Cheng, WH., Yamasaki, T., Wang, M., Ngo, CW. (eds) Advances in Multimedia Information Processing – PCM 2018. PCM 2018. Lecture Notes in Computer Science(), vol 11166. Springer, Cham. https://doi.org/10.1007/978-3-030-00764-5_52
Download citation
DOI: https://doi.org/10.1007/978-3-030-00764-5_52
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-00763-8
Online ISBN: 978-3-030-00764-5
eBook Packages: Computer ScienceComputer Science (R0)