Abstract
Image classification is an important application of deep learning. In a typical classification task, the classification accuracy is strongly related to the features that are extracted via deep learning methods. An autoencoder is a special type of neural network, often used for dimensionality reduction and feature extraction. The proposed method is based on the traditional autoencoder, incorporating the “distance” information between samples from different categories. The model is called a semi-supervised distance autoencoder. Each layer is first pre-trained in an unsupervised manner. In the subsequent supervised training, the optimized parameters are set as the initial values. To obtain more suitable features, we use a stacked model to replace the basic autoencoder structure with a single hidden layer. A series of experiments are carried out to test the performance of different models on several datasets, including the MNIST dataset, street view house numbers (SVHN) dataset, German traffic sign recognition benchmark (GTSRB), and CIFAR-10 dataset. The proposed semi-supervised distance autoencoder method is compared with the traditional autoencoder, sparse autoencoder, and supervised autoencoder. Experimental results verify the effectiveness of the proposed model.
Similar content being viewed by others
References
Bengio Y, 2009. Learning deep architectures for AI. Found Trends Mach Learn, 2(1):1–127. https://doi.org/10.1561/2200000006
Bengio Y, Courville A, Vincent P, 2013. Representation learning: a review and new perspectives. IEEE Trans Patt Anal Mach Intell, 35(8):1798–1828. https://doi.org/10.1109/tpami.2013.50
Bianco S, Buzzelli M, Schettini R, 2018. Multiscale fully convolutional network for image saliency. J Electron Imag, 27(5):051221. https://doi.org/10.1117/1.jei.27.5.051221
Deng J, Zhang ZX, Marchi E, et al., 2013. Sparse autoencoder-based feature transfer learning for speech emotion recognition. Humaine Association Conf on Affective Computing and Intelligent Interaction, p.511–516. https://doi.org/10.1109/acii.2013.90
Du F, Zhang JS, Ji NN, et al., 2018. Discriminative representation learning with supervised auto-encoder. Neur Process Lett, 49(2):507–520. https://doi.org/10.1007/s11063-018-9828-2
Feng SW, Duarte MF, 2018. Graph autoencoder-based unsupervised feature selection with broad and local data structure preservation. Neurocomputing, 312:310–323. https://doi.org/10.1016/j.neucom.2018.05.117
Glorot X, Bengio Y, 2010. Understanding the difficulty of training deep feedforward neural networks. J Mach Learn Res, 9:249–256.
Gong YC, Lazebnik S, Gordo A, et al., 2013. Iterative quantization: a procrustean approach to learning binary codes for large-scale image retrieval. IEEE Trans Patt Anal Mach Intell, 35(12):2916–2929. https://doi.org/10.1109/tpami.2012.193
Haralick RM, Shanmugam K, Dinstein I, 1973. Textural features for image classification. IEEE Trans Syst Man Cybern, SMC-3(6):610–621. https://doi.org/10.1109/TSMC.1973.4309314
He XT, Peng YX, Zhao JJ, 2018. Fast fine-grained image classification via weakly supervised discriminative localization. IEEE Trans Circ Syst Video Technol, 29(5): 1394–1407. https://doi.org/10.1109/tcsvt.2018.2834480
He XT, Peng YX, Zhao JJ, 2019. Which and how many regions to gaze: focus discriminative regions for finegrained visual categorization. Int J Comput Vis, 127(9): 1235–1255. https://doi.org/10.1007/s11263-019-01176-2
Hinton GE, 2007. Learning multiple layers of representation. Trends Cogn Sci, 11(10):428–434. https://doi.org/10.1016/j.tics.2007.09.004
Hinton GE, Salakhutdinov RR, 2006. Reducing the dimensionality of data with neural networks. Science, 313(5786):504–507. https://doi.org/10.1126/science.1127647
Kingma DP, Welling M, 2016. Auto-encoding variational Bayes. https://arxiv.org/abs/1312.6114
Meng LH, Ding SF, Zhang N, et al., 2018. Research of stacked denoising sparse autoencoder. Neur Comput Appl, 30(7): 2083–2100. https://doi.org/10.1007/s00521-016-2790-x
Meng QX, Catchpoole D, Skillicom D, et al., 2017. Relational autoencoder for feature extraction. Int Joint Conf on Neural Networks, p.364–371. https://doi.org/10.1109/ijcnn.2017.7965877
Peng YX, He XT, Zhao JJ, 2018. Object-part attention model for fine-grained image classification. IEEE Trans Image Process, 27(3):1487–1500. https://doi.org/10.1109/tip.2017.2774041
Rahmani MH, Almasganj F, Ali Seyyedsalehi S, 2018. Audiovisual feature fusion via deep neural networks for automatic speech recognition. Dig Signal Process, 82(5): 54–63. https://doi.org/10.1016/j.dsp.2018.06.004
Rifai S, Vincent P, Muller X, et al., 2011. Contractive autoencoders: explicit invariance during feature extraction. Proc 28th Int Conf on Machine Learning, p.833–840.
Santana E, Emigh M, Principe JC, 2016. Information theoretic-learning auto-encoder. Int Joint Conf on Neural Networks. https://doi.org/10.1109/ijcnn.2016.7727620
Sun Y, Chen Y, Wang XG, et al., 2014. Deep learning face representation by joint identification-verification. Proc 27th Int Conf on Neural Information Processing, p.1988–1996.
Sun YN, Xue B, Zhang MJ, et al., 2017. A particle swarm optimization-based flexible convolutional autoencoder for image classification. IEEE Trans Neur Netw Learn Syst, 30(8):2295–2309. https://doi.org/10.1109/TNNLS.2018.2881143
Taherkhani A, Cosma G, Mcginnity TM, 2018. Deep-FS: a feature selection algorithm for deep Boltzmann machines. Neurocomputing, 322:22–37. https://doi.org/10.1016/j.neucom.2018.09.040
Tang JH, Li ZC, Wang M, et al., 2015. Neighborhood discriminant hashing for large-scale image retrieval. IEEE Trans Image Process, 24(9):2827–2840. https://doi.org/10.1109/tip.2015.2421443
Tolstikhin I, Bousquet O, Gelly S, et al., 2017. Wasserstein auto-encoders. https://arxiv.org/abs/1711.01558
Vincent P, Larochelle H, Lajoie I, et al., 2010. Stacked denoising autoencoders: learning useful representations in a deep network with a local denoising criterion. J Mach Learn Res, 11(12):3371–3408.
Wang W, Huang Y, Wang YZ, et al., 2014. Generalized autoencoder: a neural network framework for dimensionality reduction. IEEE Conf on Computer Vision and Pattern Recognition. https://doi.org/10.1109/cvprw.2014.79
Wu J, Cai ZH, Zhu XQ, 2013. Self-adaptive probability estimation for Naive Bayes classification. Int Joint Conf on Neural Networks. https://doi.org/10.1109/ijcnn.2013.6707028
Xu WD, Sun HZ, Deng C, et al., 2016. Variational autoencoders for semi-supervised text classification. https://arxiv.org/abs/1603.02514
Zhang TS, Wang W, Ye H, et al., 2016. Fault detection for ironmaking process based on stacked denoising autoencoders. American Control Conf, p.3261–3267. https://doi.org/10.1109/acc.2016.7525420
Author information
Authors and Affiliations
Contributions
Liang HOU and Xiao-yi LUO designed the research and processed the data. Liang HOU drafted the manuscript. Zi-yang WANG helped organize the manuscript. Liang HOU and Jun LIANG revised and finalized the paper.
Corresponding author
Ethics declarations
Liang HOU, Xiao-yi LUO, Zi-yang WANG, and Jun LIANG declare that they have no conflict of interest.
Additional information
Project supported by the National Natural Science Foundation of China (Nos. U1664264 and U1509203)
Rights and permissions
About this article
Cite this article
Hou, L., Luo, Xy., Wang, Zy. et al. Representation learning via a semi-supervised stacked distance autoencoder for image classification. Front Inform Technol Electron Eng 21, 1005–1018 (2020). https://doi.org/10.1631/FITEE.1900116
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1631/FITEE.1900116