Discriminative Semi-supervised Learning Based on Visual Concept-Like Features

  • Fang Liu
  • Xiaofeng Wu
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 10636)


A discriminative semi-supervised learning method based on visual concept-like high-level features is proposed in this paper. Previous semi-supervised learning methods usually use unlabeled data to augment the training set or regularize the decision boundary of classifiers. The classification results rely on the precision on unlabeled data using supervised classifiers trained with limited labeled samples. When a small number of labeled samples are provided, these methods are likely to get bad results. Differently, the proposed method directly uses the distribution information of all available data in the feature space to learn a new representation which is achieved by computing the similarities of a chosen image and some discriminative data exemplars sampled from the feature space. A semi-supervised distance metric learning method by learning a projection matrix under the equivalence constraints of similar pairs and dissimilar pairs is introduced to measure these similarities, and a pseudo-mahalanobis distance is thus obtained to represent the similarities between data samples instead of Euclidean distance. Experiments showed the effectiveness of this learned distance. The new representation can be fed into standard classifiers for image classification task. The training data of our system can either be original image data or handcrafted features or image features learned by deep architectures. Therefore, the proposed method can be applied in both feature extraction and feature enhancement. In the semi-supervised classification task on eight standard datasets, the proposed method achieves improved performance over many of the previous existing methods.


Semi-supervised image classification Discriminative feature learning Metric learning 


  1. 1.
    Rosenberg, C., Hebert, M., Schneiderman, H.: Semi-supervised self-training of object detection models. In: IEEE Workshops on Application of Computer Vision, vol. 1, pp. 29–36. IEEE Computer Society (2005) Google Scholar
  2. 2.
    Rosch, E.: Principles of categorization. In: Concepts: Core Readings, pp. 189–206 (1999)Google Scholar
  3. 3.
    Shental, N., Hertz, T., Weinshall, D., Pavel, M.: Adjustment learning and relevant component analysis. In: Heyden, A., Sparr, G., Nielsen, M., Johansen, P. (eds.) ECCV 2002. LNCS, vol. 2353, pp. 776–790. Springer, Heidelberg (2002). doi: 10.1007/3-540-47979-1_52 CrossRefGoogle Scholar
  4. 4.
    Hoi, S.C., Liu, W., Lyu, M.R., Ma, W.-Y.: Learning distance metrics with contextual constraints for image retrieval. In: 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, pp. 2072–2078. IEEE (2006)Google Scholar
  5. 5.
    Cevikalp, H.: Semi-supervised discriminative common vector method for computer vision applications. Neurocomputing 129, 289–297 (2014)CrossRefGoogle Scholar
  6. 6.
    Dai, D., Van Gool, L.: Unsupervised high-level feature learning by ensemble projection for semi-supervised image classification and image clustering. arXiv preprint arXiv:1602.00955 (2016)
  7. 7.
    Lazebnik, S., Schmid, C., Ponce, J.: A sparse texture representation using local affine regions. IEEE Trans. Pattern Anal. Mach. Intell. 27, 1265–1278 (2005)CrossRefGoogle Scholar
  8. 8.
    Fei-Fei, L., Fergus, R., Perona, P.: Learning generative visual models from few training examples: an incremental bayesian approach tested on 101 object categories. Comput. Vis. Image Underst. 106, 59–70 (2007)CrossRefGoogle Scholar
  9. 9.
    Coates, A., Lee, H., Ng, A.Y.: An analysis of single-layer networks in unsupervised feature learning. In: AISTATS 2011, Ann Arbor, vol. 1001, no. 2 (2010)Google Scholar
  10. 10.
    Lazebnik, S., Schmid, C., Ponce, J.: Beyond bags of features: spatial pyramid matching for recognizing natural scene categories. In: 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, pp. 2169–2178. IEEE (2006)Google Scholar
  11. 11.
    Quattoni, A., Torralba, A.: Recognizing indoor scenes. In: IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2009, pp. 413–420. IEEE (2009)Google Scholar
  12. 12.
    Li, L.-J., Fei-Fei, L.: What, where and who? Classifying events by scene and object recognition. In: IEEE 11th International Conference on Computer Vision, ICCV 2007, pp. 1–8. IEEE (2007)Google Scholar
  13. 13.
    Xu, Z., Tao, D., Zhang, Ya., Wu, J., Tsoi, A.C.: Architectural style classification using multinomial latent logistic regression. In: Fleet, D., Pajdla, T., Schiele, B., Tuytelaars, T. (eds.) ECCV 2014. LNCS, vol. 8689, pp. 600–615. Springer, Cham (2014). doi: 10.1007/978-3-319-10590-1_39 Google Scholar
  14. 14.
    Yang, Y., Newsam, S.: Bag-of-visual-words and spatial extensions for land-use classification. In: Proceedings of the 18th SIGSPATIAL International Conference on Advances in Geographic Information Systems, pp. 270–279. ACM (2010)Google Scholar
  15. 15.
    Chatfield, K., Simonyan, K., Vedaldi, A., Zisserman, A.: Return of the devil in the details: delving deep into convolutional nets. arXiv preprint arXiv:1405.3531 (2014)
  16. 16.
    Ebert, S., Larlus, D., Schiele, B.: Extracting structures in image collections for object recognition. In: Daniilidis, K., Maragos, P., Paragios, N. (eds.) ECCV 2010. LNCS, vol. 6311, pp. 720–733. Springer, Heidelberg (2010). doi: 10.1007/978-3-642-15549-9_52 Google Scholar
  17. 17.
    Fergus, R., Weiss, Y., Torralba, A.: Semi-supervised learning in gigantic image collections. In: Advances in Neural Information Processing Systems, pp. 522–530 (2009)Google Scholar
  18. 18.
    Liu, W., He, J., Chang, S.-F.: Large graph construction for scalable semi-supervised learning. In: Proceedings of the 27th International Conference on Machine Learning (ICML 2010), pp. 679–686 (2010)Google Scholar
  19. 19.
    Pitelis, N., Russell, C., Agapito, L.: Semi-supervised learning using an unsupervised atlas. In: Calders, T., Esposito, F., Hüllermeier, E., Meo, R. (eds.) ECML PKDD 2014. LNCS, vol. 8725, pp. 565–580. Springer, Heidelberg (2014). doi: 10.1007/978-3-662-44851-9_36 Google Scholar

Copyright information

© Springer International Publishing AG 2017

Authors and Affiliations

  1. 1.Department of Electronic EngineeringFudan UniversityShanghaiChina

Personalised recommendations