Efficient Token-Guided Image-Text Retrieval With Consistent Multimodal Contrastive Training

doi:10.1109/TIP.2023.3286710

	Efficient Token-Guided Image-Text Retrieval With Consistent Multimodal Contrastive Training
	Liu, Chong 1; Zhang, Yuqi2 ; Wang, Hongsong3 ; Chen, Weihua2 ; Wang, Fan 2; Huang, Yan4 ; Shen, Yi-Dong 1; Wang, Liang4
发表期刊	IEEE TRANSACTIONS ON IMAGE PROCESSING
ISSN	1057-7149
	2023
卷号	32 页码:3622-3633
通讯作者	Wang, Hongsong(hongsongwang@seu.edu.cn) ; Chen, Weihua(kugang.cwh@alibaba-inc.com)
摘要	Image-text retrieval is a central problem for understanding the semantic relationship between vision and language, and serves as the basis for various visual and language tasks. Most previous works either simply learn coarse-grained representations of the overall image and text, or elaborately establish the correspondence between image regions or pixels and text words. However, the close relations between coarse- and fine-grained representations for each modality are important for image-text retrieval but almost neglected. As a result, such previous works inevitably suffer from low retrieval accuracy or heavy computational cost. In this work, we address image-text retrieval from a novel perspective by combining coarse- and fine-grained representation learning into a unified framework. This framework is consistent with human cognition, as humans simultaneously pay attention to the entire sample and regional elements to understand the semantic content. To this end, a Token-Guided Dual Transformer (TGDT) architecture which consists of two homogeneous branches for image and text modalities, respectively, is proposed for image-text retrieval. The TGDT incorporates both coarse- and fine-grained retrievals into a unified framework and beneficially leverages the advantages of both retrieval approaches. A novel training objective called Consistent Multimodal Contrastive (CMC) loss is proposed accordingly to ensure the intra- and inter-modal semantic consistencies between images and texts in the common embedding space. Equipped with a two-stage inference method based on the mixed global and local cross-modal similarity, the proposed method achieves state-of-the-art retrieval performances with extremely low inference time when compared with representative recent approaches. Code is publicly available: github.com/LCFractal/TGDT.
关键词	Index Terms-Image-text retrieval multimodal transformer multimodal contrastive training
DOI	10.1109/TIP.2023.3286710
收录类别	SCI
语种	英语
资助项目	Southeast University Start-Up Grant for New Faculty[RF1028623063] ; National Key Research and Development Program of China[2022ZD0117900] ; National Natural Science Foundation of China[62236010] ; National Natural Science Foundation of China[62276261]
项目资助者	Southeast University Start-Up Grant for New Faculty ; National Key Research and Development Program of China ; National Natural Science Foundation of China
WOS研究方向	Computer Science ; Engineering
WOS类目	Computer Science, Artificial Intelligence ; Engineering, Electrical & Electronic
WOS记录号	WOS:001024111100002
出版者	IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
引用统计	被引频次：3[WOS] [WOS记录] [WOS相关记录]
文献类型	期刊论文
条目标识符	http://ir.ia.ac.cn/handle/173211/53754
专题	多模态人工智能系统全国重点实验室
通讯作者	Wang, Hongsong; Chen, Weihua
作者单位	1.Chinese Acad Sci, Inst Software, State Key Lab Comp Sci, Beijing 100190, Peoples R China 2.Alibaba Grp, Beijing 100102, Peoples R China 3.Southeast Univ, Dept Comp Sci & Engn, Nanjing 210096, Peoples R China 4.Chinese Acad Sci CASIA, Inst Automat, Ctr Res Intelligent Percept & Comp CRIPAC, Natl Lab Pattern Recognit NLPR, Beijing 100190, Peoples R China
推荐引用方式 GB/T 7714	Liu, Chong,Zhang, Yuqi,Wang, Hongsong,et al. Efficient Token-Guided Image-Text Retrieval With Consistent Multimodal Contrastive Training[J]. IEEE TRANSACTIONS ON IMAGE PROCESSING,2023,32:3622-3633.
APA	Liu, Chong.,Zhang, Yuqi.,Wang, Hongsong.,Chen, Weihua.,Wang, Fan.,...&Wang, Liang.(2023).Efficient Token-Guided Image-Text Retrieval With Consistent Multimodal Contrastive Training.IEEE TRANSACTIONS ON IMAGE PROCESSING,32,3622-3633.
MLA	Liu, Chong,et al."Efficient Token-Guided Image-Text Retrieval With Consistent Multimodal Contrastive Training".IEEE TRANSACTIONS ON IMAGE PROCESSING 32(2023):3622-3633.