Unsupervised Cross-Media Retrieval Using Domain Adaptation With Scene Graph

计算机科学 判别式 图形 人工智能 域适应 图像检索 情报检索 利用 场景图 领域(数学分析) 特征学习 模式识别(心理学) 图像(数学) 理论计算机科学 计算机安全 分类器(UML) 数学 数学分析 渲染(计算机图形)
作者
Yuxin Peng,Jingze Chi
出处
期刊:IEEE Transactions on Circuits and Systems for Video Technology [Institute of Electrical and Electronics Engineers]
卷期号:30 (11): 4368-4379 被引量:32
标识
DOI:10.1109/tcsvt.2019.2953692
摘要

Existing cross-media retrieval methods are usually conducted under the supervised setting, which need lots of annotated training data. Generally, it is extremely labor-consuming to annotate cross-media data. So unsupervised cross-media retrieval is highly demanded, which is very challenging because it has to handle heterogeneous distributions across different media types without any annotated information. To address the above challenge, this paper proposes Domain Adaptation with Scene Graph (DASG) approach, which transfers knowledge from the source domain to improve cross-media retrieval in the target domain. Our DASG approach takes Visual Genome as the source domain, which contains image knowledge in the form of scene graph. The main contributions of this paper are as follows: First, we propose to address unsupervised cross-media retrieval by domain adaptation. Instead of using the labor-consuming annotated information of cross-media data in the training stage, our DASG approach learns cross-media correlation knowledge from Visual Genome, and then transfers the knowledge to cross-media retrieval through media alignment and distribution alignment. Second, our DASG approach utilizes fine-grained information via scene graph representation to enhance generalization capability across domains. The generated scene graph representation builds (subject$\rightarrow $ relationship$\rightarrow $ object) triplets by exploiting objects and relationships within image and text, which makes the cross-media correlation more precise and promotes unsupervised cross-media retrieval. Third, we exploit the related tasks including object and relationship detection for learning more discriminative features across domains. Leveraging the semantic information of objects and relationships improves cross-media correlation learning for retrieval. Experiments on two widely-used cross-media retrieval datasets, namely Flickr-30K and MS-COCO, show the effectiveness of our DASG approach.
最长约 10秒,即可获得该文献文件

科研通智能强力驱动
Strongly Powered by AbleSci AI
更新
PDF的下载单位、IP信息已删除 (2025-6-4)

科研通是完全免费的文献互助平台,具备全网最快的应助速度,最高的求助完成率。 对每一个文献求助,科研通都将尽心尽力,给求助人一个满意的交代。
实时播报
qinsu完成签到,获得积分20
1秒前
科研乞丐完成签到,获得积分10
1秒前
1秒前
2秒前
PCPCPC发布了新的文献求助10
2秒前
3秒前
量子星尘发布了新的文献求助10
3秒前
zjx0925完成签到,获得积分10
3秒前
drzz发布了新的文献求助10
3秒前
慕青应助ddddyooo采纳,获得10
3秒前
科目三应助alna采纳,获得10
4秒前
4秒前
TSY发布了新的文献求助10
4秒前
4秒前
liao完成签到,获得积分10
6秒前
6秒前
慕月发布了新的文献求助10
6秒前
熊有鹏发布了新的文献求助10
7秒前
DD应助雷雷采纳,获得10
7秒前
7秒前
7秒前
连仁兄发布了新的文献求助10
7秒前
YKH完成签到,获得积分10
7秒前
JamesPei应助范慧晨采纳,获得10
8秒前
进取拼搏发布了新的文献求助10
8秒前
9秒前
10秒前
dongdong完成签到,获得积分10
10秒前
猪猪hero发布了新的文献求助10
10秒前
11秒前
11秒前
AM发布了新的文献求助10
11秒前
12秒前
12秒前
benbenx发布了新的文献求助10
13秒前
zzz完成签到,获得积分10
14秒前
14秒前
哟哟哟完成签到 ,获得积分10
14秒前
SPQR完成签到,获得积分10
15秒前
传奇3应助迷人的冰安采纳,获得10
16秒前
高分求助中
A new approach to the extrapolation of accelerated life test data 1000
ACSM’s Guidelines for Exercise Testing and Prescription, 12th edition 500
Picture Books with Same-sex Parented Families: Unintentional Censorship 500
Nucleophilic substitution in azasydnone-modified dinitroanisoles 500
不知道标题是什么 500
A Preliminary Study on Correlation Between Independent Components of Facial Thermal Images and Subjective Assessment of Chronic Stress 500
Phylogenetic study of the order Polydesmida (Myriapoda: Diplopoda) 360
热门求助领域 (近24小时)
化学 材料科学 医学 生物 工程类 有机化学 生物化学 物理 内科学 纳米技术 计算机科学 化学工程 复合材料 遗传学 基因 物理化学 催化作用 冶金 细胞生物学 免疫学
热门帖子
关注 科研通微信公众号,转发送积分 3971333
求助须知:如何正确求助?哪些是违规求助? 3516028
关于积分的说明 11180607
捐赠科研通 3251147
什么是DOI,文献DOI怎么找? 1795693
邀请新用户注册赠送积分活动 875999
科研通“疑难数据库(出版商)”最低求助积分说明 805228