Stepwise Refinement Short Hashing for Image Retrieval

Yuan Sun, Dezhong Peng, Jian Dai, Zhenwen Ren

Abstract

Due to significant advantages in terms of storage cost and query speed, hashing learning has attracted much attention for image re- trieval. Existing hashing methods often acquiescently use long hash codes to guarantee performance, which greatly limits flexibility and scalability. Nevertheless, short hash codes are more suitable for de- vices with limited computing resources. When these methods use extremely short hash codes, it is difficult to meet the actual perfor- mance demand due to the information loss caused by the avalanche of dimension truncation. To address this issue, we propose a novel stepwise refinement short hashing (SRSH) for image retrieval that extracts critical features from high-dimensional image data to learn high-quality hash codes. Specifically, we propose a three-step cou- pled refinement strategy to relax a single hash function into three more flexible mapping matrices, such that the hash function can have more flexible to approximate precise hash codes and alleviate the information loss. Then, we adopt pairwise similarity preserving to promote coarse and fine hash codes to inherit intrinsic semantic structure from original data. Extensive experiments demonstrate the superior performance of SRSH on four image datasets.
BibTeX
@inproceedings{sun2023stepwise,
  author = {Yuan Sun and Dezhong Peng and Jian Dai and Zhenwen Ren},
  title = {{Stepwise Refinement Short Hashing for Image Retrieval}},
  booktitle = {ACM Multimedia},
  year = {2023},
  doi = {10.1145/3581783.3611864},
}

Loading related content...

Figure