Scalable Discrete and Asymmetric Unequal Length Hashing Learning for Cross-Modal Retrieval

Shaohua Teng, Jiangbo Li, Luyao Teng, Lunke Fei, Naiqi Wu, Wei ZhangIEEE Trans. Multimedia 2024 · OpenReview

Abstract

Due to the high computational efficiency and low storage cost, cross-modal hashing retrieval attracts great deal of attention. However, as heterogeneous data from different modalities often have distinct physical meanings and underlying structures, learning encoding with equal length for different modalities may result in an insurmountable semantic gap. In addition, there are other issues to be addressed in this field such as how to combine label and sample information to learn hash codes effectively, how to reduce the time consumption caused by computing $n \times n$ similarity matrix, and how to effectively solve the complex discrete optimization problem. To cope with the above challenges, this study proposes a novel model called Scalable Discrete and Asymmetric Unequal Length Hashing (SDAULH). First, SDAULH constructs a novel hash model that utilizes unequal length encoding schemes to narrow the semantic gap between heterogeneous modalities. Second, SDAULH develops a dual semantic embedding learning scheme, which combines pairwise similarity between label and sample data to generate a more discriminative hash code. Third, SDAULH associates with both hash codes and label information by an asymmetric relaxation strategy. Furthermore, SDAULH solves directly the discrete optimization problem by generating discrete hash codes. Experimental results on four benchmark datasets demonstrate the promising performance of SDAULH.
BibTeX
@article{teng2024scalable,
  author = {Shaohua Teng and Jiangbo Li and Luyao Teng and Lunke Fei and Naiqi Wu and Wei Zhang},
  title = {{Scalable Discrete and Asymmetric Unequal Length Hashing Learning for Cross-Modal Retrieval}},
  journal = {IEEE Trans. Multimedia},
  year = {2024},
  url = {https://openreview.net/forum?id=pm8iF2jATb},
}

Loading related content...

Figure