Deep Part-Based Image Feature for Clothing Retrieval

  • Laiping Zhou
  • Zhengzhong Zhou
  • Liqing Zhang
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 10636)


In this paper, we propose a straightforward way to extract part-based features only with the supervision of part-based attributes. As we know, regions can be highlighted by labels through weakly-supervised segmentation algorithms, and deep features can be extracted from CNN convolutional layers. We develop a new approach to combine them, leading to simpler procedure with only one CNN forward pass and better interpretation. We apply this method to our database of over 100,000 clothing images, and achieve comparable results to the state of the art. Moreover, the part-based features support functionalities of tuning weights among the parts, and substituting visual part features from other clothes. Because of its simplicity, the method is promising to be transferred to other image retrieval domains.


Convolutional neural networks Class activation mapping Locality-constrained linear coding Clothing retrieval 



The work was supported by the National Natural Science Foundation of China (Grant No. 91420302) and the National Basic Research Program of China (Grant No. 2015CB856004), and the Key Basic Research Program of Shanghai, China (15JC1400103).


  1. 1.
    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). doi: 10.1007/978-3-319-10590-1_38 Google Scholar
  2. 2.
    Babenko, A., Lempitsky, V.: Aggregating local deep features for image retrieval. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 1269–1277. IEEE (2015)Google Scholar
  3. 3.
    Tolias, G., Sicre, R., Jgou, H.: Particular object retrieval with integral max-pooling of CNN activations. arXiv preprint (2015). arXiv:1511.05879
  4. 4.
    Yue-Hei Ng, J., Yang, F., Davis, L.S.: Exploiting local features from deep networks for image retrieval. In: CVPR, pp. 53–61. IEEE (2015)Google Scholar
  5. 5.
    Mohedano, E., McGuinness, K., O’Connor, N.E., Salvador, A., Marqus, F., Gir-i-Nieto, X.: Bags of local convolutional features for scalable instance search. In: Proceedings of the 2016 ACM on International Conference on Multimedia Retrieval, pp. 327–331. ACM (2016)Google Scholar
  6. 6.
    Zhou, Z., Zhou, J., Zhang, L.: Demand-adaptive clothing image retrieval using hybrid topic model. In: Proceedings of the 2016 ACM on Multimedia Conference, pp. 496–500. ACM (2016)Google Scholar
  7. 7.
    Liu, Z., Luo, P., Qiu, S., Wang, X., Tang, X.: Deepfashion: powering robust clothes recognition and retrieval with rich annotations. In: CVPR, pp. 1096–1104. IEEE (2016)Google Scholar
  8. 8.
    Zhou, B., Khosla, A., Lapedriza, A., Oliva, A., Torralba, A.: Learning deep features for discriminative localization. In: CVPR, pp. 2921–2929. IEEE (2016)Google Scholar
  9. 9.
    Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition. arXiv preprint (2014). arXiv:1409.1556
  10. 10.
    Wang, J., Yang, J., Yu, K., Lv, F., Huang, T., Gong, Y.: Locality-constrained linear coding for image classification. In: CVPR, pp. 3360–3367. IEEE (2010)Google Scholar

Copyright information

© Springer International Publishing AG 2017

Authors and Affiliations

  1. 1.Key Laboratory of Shanghai Education Commission for Intelligent Interaction and Cognitive Engineering, Department of Computer Science and EngineeringShanghai Jiao Tong UniversityShanghaiChina

Personalised recommendations