Direct Hashing Without Pseudo-Labels

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 NPhard discrete optimization are successfully discarded. The experimental results demonstrate that the retrieval performance both in uni-modal and cross-modal settings can be improved.

Authors

• Feng Zheng Southern University of Science and Technology
• Heng Huang University of Maryland at College Park

Keywords

No keywords are indexed for this paper.