计算机科学
散列函数
编码(集合论)
任务(项目管理)
遗忘
哈希表
数据挖掘
计算机安全
程序设计语言
语言学
哲学
经济
集合(抽象数据类型)
管理
作者
Hao Zheng,Jinbao Wang,Xiantong Zhen,Jingkuan Song,Feng Zheng,Ke Lü,Guo-Jun Qi
标识
DOI:10.1016/j.patcog.2023.109662
摘要
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.
科研通智能强力驱动
Strongly Powered by AbleSci AI