Abstract
Deep networks have recently achieved great success in feature learning problem on various computer vision applications. Among different approaches in deep learning, unsupervised methods have attracted a lot of attention particularly to problems with limited training data. However, compared with supervised methods, unsupervised deep learning methods usually suffer from lower accuracy and higher computational time. To deal with these problems, we aim to restrict the number of connections between successive layers while enhancing discriminatory power using a data-driven approach. To this end, we propose a novel deep multi-view ensemble model. The structure of each layer is composed of an ensemble of encoders or decoders and mask operations. The multi-view ensemble of encoders or decoders enable the network to benefit from local complementary information and preserve local characteristics in final generated features, while mask operations determine the connections between successive layers. The experimental results on popular datasets indicate the effectiveness and validity of the method in clustering and classification tasks while the processing time is reduced.
Similar content being viewed by others
Notes
Stacked Auto Encoder
Convolutional Auto Encoder
Convolutional Deep Belief Network
References
Bengio Y (2013) Deep learning of representations: Looking forward, in Statistical Language and Speech Processing. Springer. p. 1-37
Bengio Y, Courville A, Vincent P (2013) Representation learning: A review and new perspectives. IEEE Trans Pattern Anal Mach Intell 35(8):1798–1828
Reed S et al (2014) Learning to disentangle factors of variation with manifold interaction. In: Proceedings of the 31st International Conference on Machine Learning (ICML-14)
Coates A, Ng AY, Lee H (2011) An analysis of single-layer networks in unsupervised feature learning. in International conference on artificial intelligence and statistics
Bengio Y, Courville AC, Vincent P (2012) Unsupervised feature learning and deep learning: A review and new perspectives. CoRR, abs/1206.5538. 1
LeCun Y, Bengio Y, Hinton G (2015) Deep learning. Nature 521(7553):436–444
Längkvist M, Karlsson L, Loutfi A (2014) A review of unsupervised feature learning and deep learning for time-series modeling. Pattern Recogn Lett 42:11–24
Bengio Y (2009) Learning deep architectures for AI. Foundations and trends® in Machine Learning 2(1):1–127
Rifai S et al (2012) Disentangling factors of variation for facial expression recognition, in Computer Vision–ECCV 2012, Springer. p. 808-822
Rifai S et al (2011) Contractive auto-encoders: Explicit invariance during feature extraction. In: Proceedings of the 28th International Conference on Machine Learning (ICML-11)
Zeiler MD (2013) Hierarchical convolutional deep learning in computer vision. Diss. New York University, New York
Chen G et al (2015) Combining unsupervised learning and discrimination for 3D action recognition. Signal Process 110:67–81
Dosovitskiy A et al (2016) Discriminative unsupervised feature learning with exemplar convolutional neural networks. IEEE Trans Pattern Anal Mach Intell 38(9):1734–1747
Kallenberg M et al (2016) Unsupervised deep learning applied to breast density segmentation and mammographic risk scoring. IEEE Trans Med Imaging 35(5):1322–1331
Erhan D et al (2009) The difficulty of training deep architectures and the effect of unsupervised pre-training. in International Conference on artificial intelligence and statistics
Erhan D et al (2010) Why does unsupervised pre-training help deep learning? The Journal of Machine Learning Research 11:625–660
Raina R, Madhavan A, Ng AY (2009) Large-scale deep unsupervised learning using graphics processors. In: Proceedings of the 26th annual international conference on machine learning. ACM
Le QV (2013) Building high-level features using large scale unsupervised learning. in Acoustics, Speech and Signal Processing (ICASSP), 2013 IEEE International Conference on. IEEE
Ouyang Y et al (2014) Autoencoder-based collaborative filtering. in International Conference on Neural Information Processing. Springer
Ng A (2011) Sparse autoencoder. CS294A Lecture notes. 72
Wu D, Sharma N, Blumenstein M (2017) Recent advances in video-based human action recognition using deep learning: A review. in Neural Networks (IJCNN), 2017 International Joint Conference on. IEEE
Du Y, Wang W, Wang L (2015) Hierarchical recurrent neural network for skeleton based action recognition. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition
Wang, L., et al. Temporal segment networks: Towards good practices for deep action recognition. in European Conference on Computer Vision. 2016. Springer
LeCun Y et al (1998) Gradient-based learning applied to document recognition. Proc IEEE 86(11):2278–2324
Krizhevsky, A. and G. Hinton, Learning multiple layers of features from tiny images. 2009
Fei-Fei L, Fergus R, Perona P (2007) Learning generative visual models from few training examples: An incremental bayesian approach tested on 101 object categories. Comput Vis Image Underst 106(1):59–70
Griffin G, Holub A, Perona P, Caltech-256 object category dataset
Zhang C et al (2017) An up-to-date comparison of state-of-the-art classification algorithms. Expert Syst Appl 82:128–150
Zhang, C., et al., Multi-Imbalance: An open-source software for multi-class imbalance learning. Knowledge-Based Systems, 2019
Wang H et al (2019) A study of graph-based system for multi-view clustering. Knowl-Based Syst 163:1009–1019
Zhang Y et al (2019) A multitask multiview clustering algorithm in heterogeneous situations based on LLE and LE. Knowl-Based Syst 163:776–786
Qiu X et al (2014) Ensemble deep learning for regression and time series forecasting. in Computational Intelligence in Ensemble Learning (CIEL), 2014 IEEE Symposium on. IEEE
Xiao Y et al (2018) A deep learning-based multi-model ensemble method for cancer prediction. Comput Methods Prog Biomed 153:1–9
Suk H-I, Lee S-W, Shen D (2017) Deep ensemble learning of sparse regression models for brain disease diagnosis. Med Image Anal 37:101–113
Yin Z et al (2017) Recognition of emotions using multimodal physiological signals and an ensemble deep learning model. Comput Methods Prog Biomed 140:93–110
Zhang X-L, Wang D (2016) A deep ensemble learning method for monaural speech separation. IEEE/ACM Transactions on Audio, Speech and Language Processing (TASLP) 24(5):967–977
Qi Z et al (2016) When ensemble learning meets deep learning: a new deep support vector machine for classification. Knowl-Based Syst 107:54–60
Zhu Z et al (2016) Deep learning representation using autoencoder for 3D shape retrieval. Neurocomputing 204:41–50
Liu M-Y, Breuel T, Kautz J (2017) Unsupervised image-to-image translation networks. Adv Neural Inf Proces Syst
Du B et al (2017) Stacked convolutional denoising auto-encoders for feature representation. IEEE Transactions on Cybernetics 47(4):1017–1027
Shen F et al (2018) Unsupervised deep hashing with similarity-adaptive and discrete optimization. IEEE Trans Pattern Anal Mach Intell
Romero A, Gatta C, Camps-Valls G (2016) Unsupervised deep feature extraction for remote sensing image classification. IEEE Trans Geosci Remote Sens 54(3):1349–1362
Yu Y et al (2018) An Unsupervised Convolutional Feature Fusion Network for Deep Representation of Remote Sensing Images. IEEE Geosci Remote Sens Lett 15(1):23–27
Zhang J, Yu J, Tao D (2018) Local deep-feature alignment for unsupervised dimension reduction. IEEE Trans Image Process 27(5):2420–2432
Orlando JI et al (2018) An ensemble deep learning based approach for red lesion detection in fundus images. Comput Methods Prog Biomed 153:115–127
Suk H-I et al (2017) Deep ensemble learning of sparse regression models for brain disease diagnosis. Med Image Anal 37:101–113
Du Y, Wang W, Wang L (2015) Hierarchical recurrent neural network for skeleton based action recognition. Proc IEEE Conf Comput Vis Pattern Recognit
Araque O et al (2017) Enhancing deep learning sentiment analysis with ensemble techniques in social applications. Expert Syst Appl 77:236–246
Bengio Y et al (2007) Greedy layer-wise training of deep networks. Adv Neural Inf Proces Syst 19:153
Schmidhuber J (2015) Deep learning in neural networks: An overview. Neural Netw 61:85–117
Yang M, Kpalma K, Ronsin J (2008) A survey of shape feature extraction techniques. In-Tech
Deb K, Jain H (2014) An evolutionary many-objective optimization algorithm using reference-point-based nondominated sorting approach, part I: Solving problems with box constraints. IEEE Trans Evolutionary Computation 18(4):577–601
Sastry K, Goldberg DE, Kendall G (2014) Genetic algorithms, in Search methodologies, Springer. p. 93-117
Michalewicz Z (2013) Genetic algorithms+ data structures= evolution programs. Springer Science & Business Media, Berlin
Abdi H, Williams LJ (2010) Principal component analysis. Wiley Interdisciplinary Reviews: Computational Statistics 2(4):433–459
Rand WM (1971) Objective criteria for the evaluation of clustering methods. J Am Stat Assoc 66(336):846–850
Hinton GE, Salakhutdinov RR (2006) Reducing the dimensionality of data with neural networks. Science 313(5786):504–507
Turchenko V, Chalmers E, Luczak A (2017) A deep convolutional auto-encoder with pooling-unpooling layers in caffe. arXiv preprint arXiv:1701.04949
Oyallon E, Mallat S (2015) Deep roto-translation scattering for object classification. in Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition
Lee H et al (2009) Convolutional deep belief networks for scalable unsupervised learning of hierarchical representations. In: Proceedings of the 26th annual international conference on machine learning, ACM
Pu Y et al (2016) A deep generative deconvolutional image model. Artificial Intelligence and Statistics
Pu Y et al (2016) Variational autoencoder for deep learning of images, labels and captions. Adv Neural Inf Proces Syst
Liu Q, Mukhopadhyay S (2018) Unsupervised Learning using Pretrained CNN and Associative Memory Bank. In: 2018 International Joint Conference on Neural Networks (IJCNN), IEEE
He K et al (2015) Spatial pyramid pooling in deep convolutional networks for visual recognition. IEEE Trans Pattern Anal Mach Intell 37(9):1904–1916
Zhao Q, Li Z (2018) Unsupervised Representation Learning with Laplacian Pyramid Auto-encoders. arXiv preprint arXiv:1801.05278
Simonyan K, Zisserman A (2014) Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556
Coates A, Ng AY (2011) Selecting receptive fields in deep networks. Adv Neural Inf Proces Syst
Lin T-H, Kung H (2014) Stable and efficient representation learning with nonnegativity constraints. International Conference on Machine Learning
Radford A, Metz L, Chintala S (2015) Unsupervised representation learning with deep convolutional generative adversarial networks. arXiv preprint arXiv:1511.06434
Gastaldi X (2017) Shake-shake regularization. arXiv preprint arXiv:1705.07485
Author information
Authors and Affiliations
Corresponding author
Additional information
Publisher’s note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
About this article
Cite this article
Koohzadi, M., Charkari, N.M. & Ghaderi, F. Unsupervised representation learning based on the deep multi-view ensemble learning. Appl Intell 50, 562–581 (2020). https://doi.org/10.1007/s10489-019-01526-0
Published:
Issue Date:
DOI: https://doi.org/10.1007/s10489-019-01526-0