Skip to main content
Springer Nature Link
Log in

Convolutional neural network feature maps selection based on LDA

  • Published:
Multimedia Tools and Applications Aims and scope Submit manuscript

Abstract

Convolutional neural network (CNN), as widely applied to vision and speech, has developed lager and lager network size in last few years. In this paper, we propose a CNN feature maps selection method which can simplify CNN structure on the premise of stabilize the classifier performance. Our approach aims to cut the feature map number of the last subsampling layer and achieves shortest runtime on the basis of Linear Discriminant Analysis (LDA). We rebuild feature maps selection formula based on the between-class scatter matrix and within-class scatter matrix, because LDA can lead to information loss in the dimension-reduction process. Our experiments measure on two standard datasets and a dataset made by ourselves. According to the separability value of each feature map, we suggest the least number of feature maps which can keep the classifier performance. Furthermore, we prove that separability value is an effective indicator for reference to select feature maps.

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
Fig. 11
Fig. 12

Similar content being viewed by others

References

  1. Chatfield K, Simonyan K, Vedaldi A, Zisserman A (2014) Return of the devil in the details: Delving deep into convolutional nets. arXiv preprint arXiv:1405.3531

  2. Chen W, Wilson JT, Tyree S, Weinberger KQ, Chen Y (2015) Compressing neural networks with the hashing trick. Comput Sci 2285–2294

  3. Courbariaux M, Bengio Y (2016) Binarynet: Training deep neural networks with weights and activations constrained to+ 1 or-1. arXiv preprint arXiv:1602.02830

  4. Deng J, Dong W, Socher R, Li LJ, Li K, Fei-Fei L (2009) Imagenet: a large-scale hierarchical image database. In: IEEE conference on computer vision and pattern recognition, 2009. CVPR 2009. pp 248–255. IEEE

  5. Duin R, Loog M (2004) Linear dimensionality reduction via a heteroscedastic extension of lda: the chernoff criterion. IEEE Transactions on Pattern Analysis and Machine Intelligence 26(6):732–739

    Article  Google Scholar 

  6. Farabet C, Couprie C, Najman L, LeCun Y (2013) Learning hierarchical features for scene labeling. IEEE Transactions on Pattern Analysis and Machine Intelligence 35(8):1915–1929

    Article  Google Scholar 

  7. Girshick R (2015) Fast r-cnn. In: Proceedings of the IEEE international conference on computer vision, pp 1440–1448

  8. Girshick R, Donahue J, Darrell T, Malik J (2014) Rich feature hierarchies for accurate object detection and semantic segmentation. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 580–587

  9. Gong Y, Liu L, Yang M, Bourdev L (2014) Compressing deep convolutional networks using vector quantization. Comput Sci

  10. Gong Y, Wang L, Guo R, Lazebnik S (2014) Multi-scale orderless pooling of deep convolutional activation features. In: European conference on computer vision. Springer, pp 392–407

  11. Han S, Mao H, Dally WJ (2015) Deep compression: Compressing deep neural network with pruning, trained quantization and huffman coding. CoRR, arXiv:1510.00149, 2

  12. Ji S, Xu W, Yang M, Yu k (2013) 3d convolutional neural networks for human action recognition. IEEE Transactions on Pattern Analysis and Machine Intelligence 35(1):221–231

    Article  Google Scholar 

  13. Krizhevsky A, Sutskever I, Hinton GE (2012) Imagenet classification with deep convolutional neural networks. In: Advances in neural information processing systems, pp 1097–1105

  14. Li H, Kadav A, Durdanovic I, Samet H, Graf HP (2016) Pruning filters for efficient convnets. arXiv preprint arXiv:1608.08710

  15. Li Y, Lu H, Li J, Li X, Li Y, Serikawa S (2016) Underwater image de-scattering and classification by deep neural network. Comput Electr Eng 54:68–77

    Article  Google Scholar 

  16. Lin M, Chen Q, Yan S (2014) Network in network. Comput Sci

  17. Liu C, Wechsler H (2002) Gabor feature based classification using the enhanced fisher linear discriminant model for face recognition. IEEE Trans Image Process 11 (4):467–476

    Article  Google Scholar 

  18. Liu J, Ren T, Wang Y, Zhong SH, Bei J, Chen S (2016) Object proposal on rgb-d images via elastic edge boxes. Neurocomputing

  19. Lu H, Li B, Zhu J, Li Y, Li Y, Xu X, He L, Li X, Li J, Serikawa S (2016) Wound intensity correction and segmentation with convolutional neural networks. Concurrency and Computation Practice and Experience

  20. Lu H, Li Y, Nakashima S, Serikawa S (2015) Single image dehazing through improved atmospheric light estimation. In: Multimedia Tools and Applications, pp 1–16

  21. Quo J, Ren T, Bei J (2016) Salient object detection for rgb-d image via saliency evolution, pp 1–6

  22. Redmon J, Divvala S, Girshick R, Farhadi A (2015) You only look once: Unified, real-time object detection. arXiv preprint arXiv:1506.02640

  23. Ren S, He K, Girshick R, Sun J (2015) Faster r-cnn: Towards real-time object detection with region proposal networks. In: Advances in neural information processing systems, pp 91–99

  24. Ren T, Liu Y, Ju R, Wu G (2016) How important is location information in saliency detection of natural images. Multimedia Tools and Applications 75(5):2543–2564

    Article  Google Scholar 

  25. Ren T, Qiu Z, Liu Y, Yu T, Bei J (2015) Soft-assigned bag of features for object tracking. Multimedia Systems 21(2):189–205

    Article  Google Scholar 

  26. Scholkopft B, Mullert KR (1999) Fisher discriminant analysis with kernels. Neural networks for signal processing IX 1(1):1

    Google Scholar 

  27. Sermanet P, Eigen D, Zhang X, Mathieu M, Fergus R, LeCun Y (2013) Overfeat: integrated recognition, localization and detection using convolutional networks. arXiv preprint arXiv:1312.6229

  28. Sharif Razavian A, Azizpour H, Sullivan J, Carlsson S (2014) Cnn features off-the-shelf: an astounding baseline for recognition. In: Proceedings of the IEEE conference on computer vision and pattern recognition workshops, pp 806–813

  29. Sun Y, Wang X, Tang X (2015) Sparsifying neural network connections for face recognition. arXiv preprint arXiv:1512.01891

  30. Szegedy C, Liu W, Jia Y, Sermanet P, Reed S, Anguelov D, Erhan D, Vanhoucke V, Rabinovich A (2015) Going deeper with convolutions. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 1–9

  31. Taigman Y, Yang M, Ranzato M, Wolf L (2014) Deepface: Closing the gap to human-level performance in face verification. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 1701–1708

  32. Zeiler MD, Fergus R (2014) Visualizing and understanding convolutional networks. In: European conference on computer vision. Springer, pp 818–833

  33. Zhang N, Paluri M, Ranzato M, Darrell T, Bourdev L (2014) Panda: Pose aligned networks for deep attribute modeling. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 1637–1644

  34. Zou WY, Wang X, Sun M, Lin Y (2014) Generic object detection with dense neural patterns and regionlets. arXiv preprint arXiv:1404.4316

Download references

Acknowledgments

This work was supported in part by National Natural Science Foundation of China: 61472444, 61472392.

Author information

Authors and Affiliations

  1. PLA University of Science and Technology, No.1 Haifu Lane, Guanghua Road, Qinhuai District, Nanjing, China

    Ting Rui, Junhua Zou, Jianchao Fei & Chengsong Yang

  2. State Key Laboratory for Novel Software Technology, Nanjing University, No.1 Haifu Lane, Guanghua Road, Qinhuai District, Nanjing, China

    Ting Rui

  3. Jiangsu Institute of Commerce, No.180 Longmian Road, Jiangning District, Nanjing, Jiangsu, China

    You Zhou

Authors
  1. Ting Rui
    View author publications

    You can also search for this author inPubMed Google Scholar

  2. Junhua Zou
    View author publications

    You can also search for this author inPubMed Google Scholar

  3. You Zhou
    View author publications

    You can also search for this author inPubMed Google Scholar

  4. Jianchao Fei
    View author publications

    You can also search for this author inPubMed Google Scholar

  5. Chengsong Yang
    View author publications

    You can also search for this author inPubMed Google Scholar

Corresponding author

Correspondence to Junhua Zou.

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Rui, T., Zou, J., Zhou, Y. et al. Convolutional neural network feature maps selection based on LDA. Multimed Tools Appl 77, 10635–10649 (2018). https://doi.org/10.1007/s11042-017-4684-z

Download citation

  • Received:

  • Revised:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s11042-017-4684-z

Keywords