Adversarial Projection Learning Based Hashing for Cross-Modal Retrieval

Cross-modal Hashing has received a lot of attentions in the field of cross-modal retrieval due to its high retrieval efficiency and low storage cost.Most of the existing cross-modal Hashing methods learn Hash codes directly from multimodal data and cannot fully utilize the semantic information of the data,so the dis-tribution consistency of low-dimensional features across modalities cannot be guaranteed.To this end,ad-versarial projection learning based Hashing for cross-modal retrieval(APLH)is proposed,which uses ad-versarial training to learn low-dimensional features from different modalities and to ensure the distribution consistency of low-dimensional features across modalities.On this basis,cross-modal projection matching constrain(CMPM)is introduced which minimizes the Kullback-Leibler divergence between feature projec-tion matching distributions and label projection matching distributions,and label information is used to align similarities between low-dimensional features of data with similarities in semantic space.Furthermore,in the Hashing learning phase,a weightedcosine triplet loss is introduced to further exploit the semantic informa-tion of the data,and to reduce the quantization loss,the Hashing function using a discrete optimization ap-proach is optimized.The mean average precision of the proposed method on three databases MIRFlickr25K,NUS-WIDE and Wikipedia is better than other methods of comparison,which verifies the effectiveness of CMPM and shows the robustness of our method.