Continuous cross-modal hashing

Zheng，Hao1; Wang，Jinbao1; Zhen，Xiantong2; Song，Jingkuan3; Zheng，Feng1; Lu，Ke4; Qi，Guo Jun5

2023-10-01

10.1016/j.patcog.2023.109662

Pattern Recognition   影响因子和分区

0031-3203

1873-5142

Generally, multimodal data with new classes arrive continuously in the real world. While advanced cross-modal hashing (CMH) focuses primarily on batch-based data with previously observed classes (ASCs), it disregards the effect of newly arriving classes (ANCs) on hash-code conflicts. In addition, class-level continuous hashing scenarios do not suit themselves well with the generic CMH configuration. To solve the aforementioned issues, we propose a novel framework, called CT-CMH, for the new task of continuous cross-modal hashing. For dealing with ANCs, CMH models require the ability of continuous learning, i.e. they can preserve the knowledge of previously observed data and, more crucially, they can be adapted to unseen data with ANCs. Specifically, we introduce the adaptive weight importance updating (AWIU) mechanism to alleviate the catastrophic forgetting problem of CMH and a new hash-code divergence (HCD) method to eliminate hash-code conflicts between ASCs and ANCs. When CT-CMH is equipped with both AWIU and HCD, it can consistently achieve high retrieval performance. The experiment results and visualization analyses validate the effectiveness of our approach. To the best of our knowledge, we are the first to introduce and implement the task of CCMH for ANCs.

Continual learning Cross-modal hashing Fast retrieval Multiple modalities

SCI ; EI

英语

第一 ; 通讯

National Natural Science Foundation of China[62122035];

Computer Science ; Engineering

Computer Science, Artificial Intelligence ; Engineering, Electrical & Electronic

WOS:001005137300001

ELSEVIER SCI LTD

20232014105424

ENGINEERING

2-s2.0-85159335120

Scopus

1.Department of Computer Science and Engineering,Southern University of Science and Technology,China
2.United Imaging Intelligence (UII) Co.,Ltd.,Beijing,China
3.School of Computer Science and Engineering,University of Electronic Science and Technology of China,China
4.School of Engineering Sciences,University of the Chinese Academy of Sciences,and the Peng Cheng Laboratory,China
5.Futurewei Technologies,Seattle,United States

Zheng，Hao,Wang，Jinbao,Zhen，Xiantong,et al. Continuous cross-modal hashing[J]. Pattern Recognition,2023,142.

Zheng，Hao.,Wang，Jinbao.,Zhen，Xiantong.,Song，Jingkuan.,Zheng，Feng.,...&Qi，Guo Jun.(2023).Continuous cross-modal hashing.Pattern Recognition,142.

Zheng，Hao,et al."Continuous cross-modal hashing".Pattern Recognition 142(2023).