Advertisement

Two-Layer Mixture Network Ensemble for Apparel Attributes Classification

  • Tianqi Han
  • Zhihui Fu
  • Hongyu Li
Conference paper
Part of the Advances in Intelligent Systems and Computing book series (AISC, volume 849)

Abstract

Recognizing apparel attributes has recently drawn great interest in the computer vision community. Methods based on various deep neural networks have been proposed for image classification, which could be applied to apparel attributes recognition. An interesting problem raised is how to ensemble these methods to further improve the accuracy. In this paper, we propose a two-layer mixture framework for ensembling different networks. In the first layer of this framework, two types of ensemble learning methods, bagging and boosting, are separately applied. Different from traditional methods, our bagging process makes use of the whole training set, not random subsets, to train each model in the ensemble, where several differentiated deep networks are used to promote model variance. To avoid the bias of small-scale samples, the second layer only adopts bagging to mix the results obtained with bagging and boosting in the first layer. Experimental results demonstrate that the proposed mixture framework outperforms any individual network model or either independent ensemble method in apparel attributes classification.

Keywords

Apparel attributes classification Boosting Ensemble Bagging 

References

  1. 1.
    Yang, M., Yu, K.: Real-time clothing recognition in surveillance videos. In: IEEE International Conferences on Image Processing (2011)Google Scholar
  2. 2.
    Kalantidis, Y., Kennedy, L., Li, L.-J.: Getting the look: clothing recognition and segmentation for automatic product suggestions in everyday photos. In: ICMR (2013)Google Scholar
  3. 3.
    Luo, Z., Luo, P., Qiu, S., Wang, X., Tang, X.: DeepFashion: powering robust clothes recognition and retrieval with rich annotations. In: Proceeding of IEEE Conferences on Computer Vision and Pattern Recognition (2016)Google Scholar
  4. 4.
    Dorogush, A.V., Ershov, V., Gulin, A.: CatBoost: gradient boosting with categorical features support. In: Workshops on ML Systems at NIPS (2017)Google Scholar
  5. 5.
    Chen, T., Carlos, G.: XGBoost: a scalable tree boosting system. In: KDD (2016)Google Scholar
  6. 6.
    Breiman, L.: Bagging predictors. Mach. Learn. 24(2), 123–140 (1996)MathSciNetzbMATHGoogle Scholar
  7. 7.
    He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: Proceeding of IEEE Conferences on Computer Vision and Pattern Recognition (2016)Google Scholar
  8. 8.
    Hu, J., Shen, L., Sun, G.: Squeeze-and-excitation networks. In: arXiv preprint arXiv:1709.01507
  9. 9.
    Szegedy, C., Ioffe, S., Vanhouke, V., Alemi, A.A.: Inception-V4, inception-resnet and the impact of residual connections on learning. In: AAAI (2017)Google Scholar
  10. 10.
    Huang, G., Liu, Z., van der Maaten, L., Weinberger, K.: Densely connected convolutional networks. In: Proceeding of IEEE Conferences on Computer Vision and Pattern Recognition (2017)Google Scholar
  11. 11.
    Russakovsky, O., Deng, J., Su, H., Krause, J., Satheesh, S., Ma, S., Huang, Z., Karpathy, A., Khosla, A., Bernstein, M., Berg, A.C., Fei-Fei, L.: ImageNet large scale visual recognition challenge. In: IJCV (2015)Google Scholar

Copyright information

© Springer Nature Switzerland AG 2019

Authors and Affiliations

  1. 1.AI LabZhongAn Information Technology Service Co., Ltd.ShanghaiChina

Personalised recommendations