Deep Multi-Similarity Hashing with semantic-aware preservation for multi-label image retrieval

作者：

Highlights：

• CNNs with correlation operators are introduced to capture higher-order features.

• A semantic-aware method is proposed to quantify the similarity of image pairs.

• Multi-similarity loss is developed to collect informative pairs efficiently.

• The state-of-the-art results are reported on three benchmark datasets.

摘要

•CNNs with correlation operators are introduced to capture higher-order features.•A semantic-aware method is proposed to quantify the similarity of image pairs.•Multi-similarity loss is developed to collect informative pairs efficiently.•The state-of-the-art results are reported on three benchmark datasets.

论文关键词：Deep hashing,Image retrieval,Higher-order features,Semantic-aware similarity,Multi-similarity loss

论文评审过程：Received 24 December 2021, Revised 28 March 2022, Accepted 27 May 2022, Available online 3 June 2022, Version of Record 10 June 2022.

论文官网地址：https://doi.org/10.1016/j.eswa.2022.117674