Semantic Structure Enhanced Contrastive Adversarial Hash Network for Cross-media Representation Learning

MeiYu Liang, Junping Du, Xiaowen Cao, Yang Yu, Kangkang Lu, Zhe Xue, Min Zhang

Abstract

Deep cross-media hashing technology provides an efficient cross-media representation learning solution for cross-media search. However, the existing methods do not consider both fine-grained semantic features and semantic structures to mine implicit cross-media semantic associations, which leads to weaker semantic discrimination and consistency for cross-media representation. To tackle this problem, we propose a novel semantic structure enhanced contrastive adversarial hash network for cross-media representation learning (SCAHN). Firstly, in order to capture more fine-grained cross-media semantic associations, a fine-grained cross-media attention feature learning network is constructed, thus the learned saliency features of different modalities are more conducive to cross-media semantic alignment and fusion. Secondly, for further improving learning ability of implicit cross-media semantic associations, a semantic label association graph is constructed, and the graph convolutional network is utilized to mine the implicit semantic structures, thus guiding learning of discriminative features of different modalities. Thirdly, a cross-media and intra-media contrastive adversarial representation learning mechanism is proposed to further enhance the semantic discriminativeness of different modal representations, and a dual-way adversarial learning strategy is developed to maximize cross-media semantic associations, so as to obtain cross-media unified representations with stronger discriminativeness and semantic consistency preserving power. Extensive experiments on several cross-media benchmark datasets demonstrate that the proposed SCAHN outperforms the state-of-the-art methods.
BibTeX
@inproceedings{liang2022semantic,
  author = {MeiYu Liang and Junping Du and Xiaowen Cao and Yang Yu and Kangkang Lu and Zhe Xue and Min Zhang},
  title = {{Semantic Structure Enhanced Contrastive Adversarial Hash Network for Cross-media Representation Learning}},
  booktitle = {ACM Multimedia},
  year = {2022},
  doi = {10.1145/3503161.3548391},
}

Loading related content...

Figure