Deep Weibull hashing with maximum mean discrepancy quantization for image retrieval

Abstract

Hashing has been a promising technology for fast nearest neighbor retrieval in large-scale datasets due to the low storage cost and fast retrieval speed. Most existing deep hashing approaches learn compact hash codes through pair-based deep metric learning such as the triplet loss. However, these methods often consider that the intra-class and inter-class similarity make the same contribution, and consequently it is difficult to assign larger weights for informative samples during the training procedure. Furthermore, only imposing relative distance constraint increases the possibility of being clustered with larger average intra-class distance for similar pairs, which is harmful to learning a high separability Hamming space. To tackle the issues, we put forward deep Weibull hashing with maximum mean discrepancy quantization (DWH), which jointly performs neighborhood structure optimization and error-minimizing quantization to learn high-quality hash codes in a unified framework. Specifically, DWH learns the desired neighborhood structure in conjunction with a flexible pair similarity optimization strategy and a Weibull distribution-based constraint between anchors and their neighbors in Hamming space. More importantly, we design a maximum mean discrepancy quantization objective function to preserve the pairwise similarity when performing binary quantization. Besides, a class-level loss is introduced to mine the semantic structural information of images by using supervision information. The encouraging experimental results on various benchmark datasets demonstrate the efficacy of the proposed DWH.