Browse

Efficient end-to-end learning for quantizable representations

Cited 0 time in Web of Science Cited 0 time in Scopus
Issue Date
2018-01
Publisher
International Machine Learning Society (IMLS)
Citation
35th International Conference on Machine Learning, ICML 2018, Vol.5, pp.3550-3559
Abstract
© 2018 by authors.All right reserved. Embedding representation learning via neural networks is at the core foundation of modern similarity based search. While much effort has been put in developing algorithms for learning binary hamming code representations for search efficiency,: this still requires a linear scan of the entire dataset per each query and trades off the search accuracy through binarization. To this end, we consider the problem of directly learning a quantizable embedding representation and the sparse binary hash code end-to-end which can be used to construct an efficient hash table not only providing significant search reduction in the number of data but also achieving the state of the art search accuracy outperforming previous state of the art deep metric; learning methods. We also show that finding the optimal sparse binary hash code in a mini-batch can be computed exactly in polynomial time by solving a minimum cost flow problem. Our results on Cifar-100 and on ImageNet dataseis show the state of the art search accuracy in precision@k and NMI metrics while providing up to 98× and 478× search speedup respectively over exhaustive linear search. The source code is available at https://github.com/maestrojeong/Deep-Hash-Table-ICML18.
URI
https://hdl.handle.net/10371/179346
Files in This Item:
There are no files associated with this item.
Appears in Collections:
College of Engineering/Engineering Practice School (공과대학/대학원)Dept. of Computer Science and Engineering (컴퓨터공학부)Journal Papers (저널논문_컴퓨터공학부)
  • mendeley

Items in S-Space are protected by copyright, with all rights reserved, unless otherwise indicated.

Browse