SCE-MSPFS: A Novel Deep Convolutional Feature Selection Method for Image Retrieval

  • Dong-dong Niu
  • Yong FengEmail author
  • Jia-xing Shang
  • Bao-hua Qiang
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 11306)


Effective image features are of vital importance for content-based image retrieval task. Recently, deep convolutional neural networks have been widely used in learning image features and have achieved promising results. However, there are still two questions need to be addressed. The first is the limitation of the image size in some works, and the second is the convolutional feature may not directly suitable for image retrieval. In our paper, we comprehensively solve these two problems by proposing a novel feature selection approach based on a pre-trained CNNs. Compared with others feature selection methods, our approach takes a two-stage strategy. The first stage is to select the effective feature sets using our proposed Median Sum Pooling Feature Selection method, and the second stage boosts the selected feature sets using the Space Channel Enhancement model. We evaluate our method on three benchmark datasets including Oxford5K, Paris6K, and Holiday. The experimental results show that our proposed method achieves competitive performance on both Oxford and Paris buildings benchmarks.


Image retrieval Feature selection Convolutional neural networks 



This work was supported by National Nature Science Foundation of China (No. 61762025), Frontier and Application Foundation Research Program of CQ CSTC (No. cstc2017jcyjAX0340), The National Key Research and Development Program of China (No. 2017YFB1402400), Guangxi Key Laboratory of Trusted Software (No.kx201701), Guangxi Cooperative Innovation Center of Cloud Computing and Big Data (No.YD16E01), and Key Industries Common Key Technologies Innovation Projects of CQ CSTC (No. cstc2017zdcy-zdyxx0047), Chongqing Postdoctoral Science Foundation (No. Xm2017125), Social Undertakings and Livelihood Security Science and Technology Innovation Funds of CQ CSTC (No. cstc2017shmsA20013).


  1. 1.
    Lowe, D.G.: Object recognition from local scale-invariant features. In: ICCV, pp. 1150–1157 (1999)Google Scholar
  2. 2.
    Jegou, H., Douze, M., Schmid, C.: On the burstiness of visual elements. In: CVPR, pp. 1169–1176. IEEE Computer Society (2009)Google Scholar
  3. 3.
    Krizhevsky, A., Sutskever, I., Hinton, G.E.: Imagenet classification with deep convolutional neural networks. In: NIPS, pp. 1106–1114 (2012)Google Scholar
  4. 4.
    Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition. CoRR abs/1409.1556 (2014)Google Scholar
  5. 5.
    Girshick, R.B., Donahue, J., Darrell, T., Malik, J.: Rich feature hierarchies for accurate object detection and semantic segmentation. CoRR abs/1311.2524 (2013)Google Scholar
  6. 6.
    Long, J., Shelhamer, E., Darrell, T.: Fully convolutional networks for semantic segmentation. In: CVPR, pp. 3431–3440. IEEE Computer Society (2015)Google Scholar
  7. 7.
    Arandjelovic, R., Gronát, P., Torii, A., Pajdla, T., Sivic, J.: Netvlad: CNN architecture for weakly supervised place recognition. In: CVPR, pp. 5297–5307. IEEE Computer Society (2016)Google Scholar
  8. 8.
    Babenko, A., Lempitsky, V.S.: Aggregating deep convolutional features for image retrieval. CoRR abs/1510.07493 (2015)Google Scholar
  9. 9.
    Gordo, A., Almazán, J., Revaud, J., Larlus, D.: Deep image retrieval: learning global representations for image search. CoRR abs/1604.01325 (2016)Google Scholar
  10. 10.
    Kalantidis, Y., Mellina, C., Osindero, S.: Cross-dimensional weighting for aggregated deep convolutional features. CoRR abs/1512.04065 (2015)Google Scholar
  11. 11.
    Tolias, G., Sicre, R., Jégou, H.: Particular object retrieval with integral max-pooling of CNN activations. CoRR abs/1511.05879 (2015)Google Scholar
  12. 12.
    Wei, X., Luo, J., Wu, J.: Selective convolutional descriptor aggregation for fine-grained image retrieval. CoRR abs/1604.04994 (2016)Google Scholar
  13. 13.
    Hu, J., Shen, L., Sun, G.: Squeeze-and-excitation networks. CoRR abs/1709.01507 (2017)Google Scholar
  14. 14.
    Zeiler, M.D., Fergus, R.: Visualizing and understanding convolutional networks. In: Fleet, D., Pajdla, T., Schiele, B., Tuytelaars, T. (eds.) ECCV 2014. LNCS, vol. 8689, pp. 818–833. Springer, Cham (2014). Scholar
  15. 15.
    Jegou, H., Douze, M., Schmid, C.: Improving bag-of-features for large scale image search. Int. J. Comput. Vis. 87(3), 316–336 (2010)CrossRefGoogle Scholar
  16. 16.
    Philbin, J., Chum, O., Isard, M., Sivic, J., Zisserman, A.: Object retrieval with large vocabularies and fast spatial matching. In: CVPR. IEEE Computer Society (2007)Google Scholar
  17. 17.
    Philbin, J., Chum, O., Isard, M., Sivic, J., Zisserman, A.: Lost in quantization: Improving particular object retrieval in large scale image databases. In: CVPR. IEEE Computer Society (2008)Google Scholar
  18. 18.
    Jégou, H., Zisserman, A.: Triangulation embedding and democratic aggregation for image search. In: CVPR, pp. 3310–3317. IEEE Computer Society (2014)Google Scholar
  19. 19.
    Babenko, A., Slesarev, A., Chigorin, A., Lempitsky, V.: Neural codes for image retrieval. In: Fleet, D., Pajdla, T., Schiele, B., Tuytelaars, T. (eds.) ECCV 2014. LNCS, vol. 8689, pp. 584–599. Springer, Cham (2014). Scholar
  20. 20.
    Gong, Y., Wang, L., Guo, R., Lazebnik, S.: Multi-scale orderless pooling of deep convolutional activation features. In: Fleet, D., Pajdla, T., Schiele, B., Tuytelaars, T. (eds.) ECCV 2014. LNCS, vol. 8695, pp. 392–407. Springer, Cham (2014). Scholar
  21. 21.
    Ren, S., He, K., Girshick, R.B., Sun, J.: Faster R-CNN: towards real-time object detection with region proposal networks. CoRR abs/1506.01497 (2015)Google Scholar

Copyright information

© Springer Nature Switzerland AG 2018

Authors and Affiliations

  • Dong-dong Niu
    • 1
    • 2
  • Yong Feng
    • 1
    • 2
    Email author
  • Jia-xing Shang
    • 1
    • 2
  • Bao-hua Qiang
    • 3
    • 4
  1. 1.College of Computer Science, Chongqing UniversityChongqingChina
  2. 2.Key Laboratory of Dependable Service Computing in Cyber Physical Society, Ministry of EducationChongqing UniversityChongqingChina
  3. 3.Guangxi Key Laboratory of Trusted SoftwareGuilin University of Electronic TechnologyGuilinChina
  4. 4.Guangxi Cooperative Innovation Center of cloud computing and Big DataGuilin University of Electronic TechnologyGuilinChina

Personalised recommendations