Skip to main content
Springer Nature Link
Log in

Guided autoencoder for dimensionality reduction of pedestrian features

  • Published:
Applied Intelligence Aims and scope Submit manuscript

Abstract

Autoencoder and other conventional dimensionality reduction algorithms have achieved great success in dimensionality reduction. In this paper, we present an improved autoencoder structure, which was applied it in the field of pedestrian feature dimensionality reduction. The novel method is also verified on Mnist dataset. High-dimensional deep pedestrian features outperform other descriptors while it is challenging for computing capability and memory in existing systems. The dimensionality reduction method we proposed takes advantages of autoencoder and principal component analysis to achieve high efficiency. A novel weight matrix initialization and an improved reconstruction of autoencoder are proposed. Furthermore, by fusing features labeled with the same pedestrian, the proposed structure minimizes the loss after dimensionality reduction. Experimental results demonstrate that our method outperforms traditional dimensionality reduction methods. In the experiment, the pedestrian features were generated by ResNet and Market-1501 data-set. Our method achieves up to 8.834% mAP increment compared to a principal component analysis, when 2048-dimension pedestrian features are reduced to 16-dimension features.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Subscribe and save

Springer+ Basic
$34.99 /Month
  • Get 10 units per month
  • Download Article/Chapter or eBook
  • 1 Unit = 1 Article or 1 Chapter
  • Cancel anytime
Subscribe now

Buy Now

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6
Fig. 7
Fig. 8
Fig. 9
Fig. 10

Similar content being viewed by others

Explore related subjects

Discover the latest articles, news and stories from top researchers in related subjects.

References

  1. Zhang Y, Zhang Z, Zhang Z et al (2020) Deep self-representative concept factorization network for representation learning[C]. In: Proceedings of the 2020 SIAM international conference on data mining. Society for Industrial and Applied Mathematics, pp 361–369

  2. Zhang Z, Li F, Zhao M et al (2017) Robust neighborhood preserving projection by nuclear/l2, 1-norm regularization for image feature extraction[J]. IEEE Trans Image Process 26(4):1607–1622

    Article  MathSciNet  Google Scholar 

  3. Zhang Y, Zhang Z, Li S et al (2018) Unsupervised nonnegative adaptive feature extraction for data representation[J]. IEEE Trans Knowl Data Eng 31(12):2423–2440

    Article  MathSciNet  Google Scholar 

  4. Ye Q, Li Z, Fu L et al (2019) Nonpeaked discriminant analysis for data representation[J]. IEEE Trans Neural Netw Learning Sys 30(12):3818–3832

    Article  MathSciNet  Google Scholar 

  5. Mahmood A, Bennamoun M, An S et al (2019) Deep image representations for coral image classification. IEEE J Ocean Eng 44(1):121–131

    Article  Google Scholar 

  6. Li Chen, Wang Kai, Xu N (2017) A survey for the applications of content-based microscopic image analysis in microorganism classification domains. Artif Intell Rev 51:1–70

    Google Scholar 

  7. Yi Hou, Hong Z, Zhou S (2017) BoCNF: efficient image matching with bag of ConvNet features for scalable and robust visual place recognition. Auton Robot 42:1–17

    Google Scholar 

  8. Yang Wei, Zhong Liming et al (2017) Lin predicting CT image from MRI data through feature matching with learned nonlinear local descriptors. IEEE Trans Med Imaging PP:977

    Google Scholar 

  9. Tsochatzidis L, Zagoris K et al (2017) Arikidis computer-aided diagnosis of mammographic masses based on a supervised content-based image retrieval approach. Pattern Recogn 71:106–117

    Article  Google Scholar 

  10. Lu X, Zheng X, Li X (2017) Latent semantic minimal hashing for image retrieval. IEEE Transactions on Image Processing 26:355–368

    Article  MathSciNet  Google Scholar 

  11. Carcenac M, Redif S (2015) A highly scalable modular bottleneck neural network for image dimensionality reduction and image transformation. Appl Intell 44:557–610

    Article  Google Scholar 

  12. Yang YB, Li YN, Pan LY, Li N, He GN (2013) Image retrieval based on augmented relational graph representation. Appl Intell 38:489–50

    Article  Google Scholar 

  13. Hosoya H, Hyvärinen A (2016) Learning visual spatial pooling by strong PCA dimension reduction. Neural Comput 28:1249–1264

    Article  MathSciNet  Google Scholar 

  14. Wold S, Esbensen K, Geladi P (1987) Principal component analysis. Chemometrics and Intelligent Laboratory Systems 2:37–52

    Article  Google Scholar 

  15. Shu X, Lu H (2014) Linear discriminant analysis with spectral regularization. Appl Intell 40:724–731

    Article  Google Scholar 

  16. Laohakiat S, Phimoltares S, Lursinsap C (2017) A clustering algorithm for stream data with LDA-based unsupervised localized dimension reduction. Journal 381:104–123

    Google Scholar 

  17. Gao G, Liu L, Wang L, Zhang Y (2019) Fashion clothes matching scheme based on Siamese Network and AutoEncoder. Multimedia Systems 25:593–602

    Article  Google Scholar 

  18. Kim M, Lee W, Cho D-H (2017) A novel PAPR reduction scheme for OFDM system based on deep learning. IEEE Commun Lett 22:510–513

    Article  Google Scholar 

  19. Van Der Maaten L (2014) Accelerating t-SNE using tree-based algorithms. The Journal of Machine Learning Research 15:3221–3245

    MathSciNet  MATH  Google Scholar 

  20. Zhou H, Wang F, Tao P (2018) T-distributed stochastic neighbor embedding method with the least information loss for macromolecular simulations. Journal of Chemical Theory and Computation 14:5499–5510

    Article  Google Scholar 

  21. Li T, Li M, Gao Q, Xie D (2017) F-norm distance metric based robust 2DPCA and face recognition. Neural Netw 94:204–211

    Article  Google Scholar 

  22. Wang Q, Gao Q, Gao X, Nie F (2017) ℓ2,p-Norm based PCA for image recognition. IEEE Transactions on Image Processing 27:1336–1346s

    Article  MathSciNet  Google Scholar 

  23. Hinton GE, Salakhutdinov RR (2006) Reducing the dimensionality of data with neural networks. Science 313:504–507

    Article  MathSciNet  Google Scholar 

  24. Wang W, Huang Y, Wang Y, Wang L (2014) Generalized autoencoder: a neural network framework for dimensionality reduction. In: Proceedings of the IEEE conference on computer vision and pattern recognition workshops, pp 490–497

  25. Zhao C (2016) An autoencoder-based image descriptor for image matching and retrieval

  26. Petscharnig S, Lux M, Chatzichristofis S (2017) Dimensionality reduction for image features using deep learning and autoencoders. In: Proceedings of the 15th international workshop on content-based multimedia indexing, pp 1–6

  27. Baldi P, Hornik K (1989) Neural networks and principal component analysis: Learning from examples without local minima. Neural Networks 2:53–58

    Article  Google Scholar 

  28. Sperduti A et al (2003) Linear autoencoder networks for structured data. International Workshop on Neural-Symbolic Learning and Reasoning

  29. Ou J, Li Y, Shen C (2018) Unlabeled PCA-shuffling initialization for convolutional neural networks. Appl Intell 48:4565–4576

    Article  Google Scholar 

  30. Zhang Y, Zhang Z, Qin J et al (2018) Semi-supervised local multi-manifold Isomap by linear embedding for feature extraction[J]. Pattern Recogn 76:662–678

    Article  Google Scholar 

  31. Xiao Q, Dai J, Luo J et al (2019) Multi-view manifold regularized learning-based method for prioritizing candidate disease miRNAs[j]. Knowl-Based Syst 175:118–129

    Article  Google Scholar 

  32. Wang H, Yang Y, Liu B et al (2019) A study of graph-based system for multi-view clustering[J]. Knowl-Based Syst 163:1009–1019

    Article  Google Scholar 

Download references

Author information

Authors and Affiliations

  1. School of Electrical and Information Engineering, Tianjin University, No. 92 Weijin Road, Nankai District, Tianjin, China

    Xuan Li, Tao Zhang, Xin Zhao & Zhengming Yi

Authors
  1. Xuan Li
    View author publications

    You can also search for this author inPubMed Google Scholar

  2. Tao Zhang
    View author publications

    You can also search for this author inPubMed Google Scholar

  3. Xin Zhao
    View author publications

    You can also search for this author inPubMed Google Scholar

  4. Zhengming Yi
    View author publications

    You can also search for this author inPubMed Google Scholar

Corresponding author

Correspondence to Tao Zhang.

Additional information

Publisher’s note

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Li, X., Zhang, T., Zhao, X. et al. Guided autoencoder for dimensionality reduction of pedestrian features. Appl Intell 50, 4557–4567 (2020). https://doi.org/10.1007/s10489-020-01813-1

Download citation

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s10489-020-01813-1

Keywords