A. Babenko, A. Slesarev, A. Chigorin, and V. S. Lempitsky. Neural codes for image retrieval. In Conference on Computer Vision, pages 584–599, 2014.

Babenko et al. demonstrate the usage of deep convolutional neural networks, based on the architecture by Krizhevsky et al. [1], for image retrieval. They report promising results, especially when re-training networks on appropriate datasets and using different compression techniques. Unfortunately, the implementation as well as the dataset for re-training are not publicly available - merely a list (in Russian) corresponding to the keywords used for the Yandex search engine is provided (see here). However, Babenko et al. claim that a custom version of the original implementation (available here) by Krizhevsky et al. is used. The effectiveness of different layers for image retrieval is compared to several state-of-the-art approaches [2,3,4,5].

  • [1] A. Krizhevsky, I. Sutskever, and G. E. Hinton. ImageNet classification with deep convolutional neural networks. In Advances in Neural Information Processing Systems, pages 1106–1114, 2012.
  • [2] A. Gordo, J. A. Rodríguez-Serrano, F. Perronnin, E. Valveny. Leveraging category-level labels for instance-level image retrieval. In Conference on Computer Vision and Pattern Recognition, pages 3045–3052, 2012.
  • [3] R. Arandjelovic, A. Zisserman. All about VLAD. In Conference on Computer Vision and Pattern Recognition, pages 1578–1585, 2013.
  • [4] T. Ge, Q. Ke, J. Sun. Sparse-coded features for image retrieval. In British Machine Vision Conference, 2013.
  • [5] H. Jégou, A. Zisserman. Triangulation embedding and democratic aggregation for image search. In Conference on Computer Vision and Pattern Recognition, pages 3310–3317, 2014.
What is your opinion on this article? Let me know your thoughts on Twitter @davidstutz92 or LinkedIn in/davidstutz92.