Deep Unsupervised Hashing with Latent Semantic Components


  • Qinghong Lin Shenzhen University
  • Xiaojun Chen Shenzhen University
  • Qin Zhang Shenzhen University
  • Shaotian Cai Shenzhen University
  • Wenzhe Zhao Tencent Computer System Co., Ltd.
  • Hongfa Wang Tencent Computer System Co., Ltd.



Machine Learning (ML), Computer Vision (CV)


Deep unsupervised hashing has been appreciated in the regime of image retrieval. However, most prior arts failed to detect the semantic components and their relationships behind the images, which makes them lack discriminative power. To make up the defect, we propose a novel Deep Semantic Components Hashing (DSCH), which involves a common sense that an image normally contains a bunch of semantic components with homology and co-occurrence relationships. Based on this prior, DSCH regards the semantic components as latent variables under the Expectation-Maximization framework and designs a two-step iterative algorithm with the objective of maximum likelihood of training data. Firstly, DSCH constructs a semantic component structure by uncovering the fine-grained semantics components of images with a Gaussian Mixture Modal~(GMM), where an image is represented as a mixture of multiple components, and the semantics co-occurrence are exploited. Besides, coarse-grained semantics components, are discovered by considering the homology relationships between fine-grained components, and the hierarchy organization is then constructed. Secondly, DSCH makes the images close to their semantic component centers at both fine-grained and coarse-grained levels, and also makes the images share similar semantic components close to each other. Extensive experiments on three benchmark datasets demonstrate that the proposed hierarchical semantic components indeed facilitate the hashing model to achieve superior performance.




How to Cite

Lin, Q., Chen, X., Zhang, Q., Cai, S., Zhao, W., & Wang, H. (2022). Deep Unsupervised Hashing with Latent Semantic Components. Proceedings of the AAAI Conference on Artificial Intelligence, 36(7), 7488-7496.



AAAI Technical Track on Machine Learning II