Direct Hashing Without Pseudo-Labels

Authors

  • Feng Zheng University of Pittsburgh
  • Heng Huang Univerisity of Pittsburgh

Keywords:

Hamming, Binary Codes, Quantization Loss, Pseudo-Label

Abstract

Recently, binary hashing has been widely applied to data compression, ranking and nearest-neighbor search. Although some promising results have been achieved, effectively optimizing sign function related objectives is still highly challenging and thus pseudo-labels are inevitably used. In this paper, we propose a novel general framework to simultaneously minimize the measurement distortion and the quantization loss, which enable to learn hash functions directly without requiring the pseudo-labels. More significantly, a novel W-Shape Loss (WSL) is specifically developed for hashing so that both the two separate steps of relaxation and the NP-hard discrete optimization are successfully discarded. The experimental results demonstrate that the retrieval performance both in uni-modal and cross-modal settings can be improved.

Downloads

Published

2018-04-29

How to Cite

Zheng, F., & Huang, H. (2018). Direct Hashing Without Pseudo-Labels. Proceedings of the AAAI Conference on Artificial Intelligence, 32(1). Retrieved from https://ojs.aaai.org/index.php/AAAI/article/view/11675