2022/06/06 by Shichao Zhang, Zhang, Shichao, Jiaye Li +1
Computer Science · #Advanced Image and Video Retrieval Techniques #FOS: Computer and information sciences #Face and Expression Recognition #Machine Learning (cs.LG) #Text and Document Classification Technologies
paper · pdf · doi:10.48550/arxiv.2206.02334
openalex publication_date 2022/06/06 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28
Existing unsupervised hash learning is a kind of attribute-centered calculation. It may not accurately preserve the similarity between data. This leads to low down the performance of hash function learning. In this paper, a hash algorithm is proposed with a hyper-class representation. It is a two-steps approach. The first step finds potential decision features and establish hyper-class. The second step constructs hash learning based on the hyper-class information in the first step, so that the hash codes of the data within the hyper-class are as similar as possible, as well as the hash codes of the data between the hyper-classes are as different as possible. To evaluate the efficiency, a series of experiments are conducted on four public datasets. The experimental results show that the proposed hash algorithm is more efficient than the compared algorithms, in terms of mean average precision (MAP), average precision (AP) and Hamming radius 2 (HAM2)