Self-Training Based Semi-Supervised and Semi-Paired Hashing Cross-Modal Retrieval
Rongrong Jing1,2; Hu Tian1,2; Xingwei Zhang1,2; Gang Zhou1,2; Xiaolong Zheng1,2; Dajun Zeng1,2
2022-07
会议名称The 2022 International Joint Conference on Neural Networks (IJCNN)
会议日期2022-07
会议地点Padua, Italy
摘要

The aim of cross-modal retrieval is to search for flexible results across different types of multimedia data. However, the labeled data is usually limited and not well paired with different modalities in practical applications. These issues are not well addressed in the existing works, which cannot consider the semantic information about unlabeled and unpaired data, synchronously. Self-training is a well-known strategy to handle semi-supervised problems. Motivated by the self-training, this paper proposes a self-training-based cross-modal hashing framework (STCH) to tackle the semi-supervised and semi-paired challenges. In the framework, graph neural networks are used to capture potential intra-modality and inter-modality similarities to produce pseudo labels. Then the inconsistent pseudo labels of different modalities are refined with a heuristic filter to enhance the model robustness. To train STCH, we propose an alternating learning strategy to conduct the self-train by predicting pseudo labels during the training procedure, which can be seamlessly incorporated into semi-supervised and supervised learning. In this way, the proposed method can leverage sufficient semantic information to enhance the semi-supervised effect and address the semi-paired problem. Experiments on the real-world datasets demonstrate that our approach outperforms related methods on hash cross-modal retrieval.

文献类型会议论文
条目标识符http://ir.ia.ac.cn/handle/173211/48818
专题复杂系统管理与控制国家重点实验室_互联网大数据与信息安全
通讯作者Xiaolong Zheng
作者单位1.Institute of Automation, Chinese Academy of Sciences
2.University of Chinese Academy of Sciences
第一作者单位中国科学院自动化研究所
通讯作者单位中国科学院自动化研究所
推荐引用方式
GB/T 7714
Rongrong Jing,Hu Tian,Xingwei Zhang,et al. Self-Training Based Semi-Supervised and Semi-Paired Hashing Cross-Modal Retrieval[C],2022.
条目包含的文件 下载所有文件
文件名称/大小 文献类型 版本类型 开放类型 使用许可
ijcnn_v23.pdf(682KB)会议论文 开放获取CC BY-NC-SA浏览 下载
个性服务
推荐该条目
保存到收藏夹
查看访问统计
导出为Endnote文件
谷歌学术
谷歌学术中相似的文章
[Rongrong Jing]的文章
[Hu Tian]的文章
[Xingwei Zhang]的文章
百度学术
百度学术中相似的文章
[Rongrong Jing]的文章
[Hu Tian]的文章
[Xingwei Zhang]的文章
必应学术
必应学术中相似的文章
[Rongrong Jing]的文章
[Hu Tian]的文章
[Xingwei Zhang]的文章
相关权益政策
暂无数据
收藏/分享
文件名: ijcnn_v23.pdf
格式: Adobe PDF
所有评论 (0)
暂无评论
 

除非特别说明,本系统中所有内容都受版权保护,并保留所有权利。