CASIA OpenIR  > 多模态人工智能系统全国重点实验室  > 多媒体计算
Part-aware Prompt Tuning For Weakly Supervised Referring Expression Grounding
Chenlin, Zhao1,2,3; Jiabo, Ye3,5; Yaguang, Song4; Ming, Yan3; Xiaoshan, Yang1,2,4; Changsheng, Xu1,2,4
2024-01-29
Conference Namethe 30th International Conference on MultiMedia Modeling
Conference Date2024-1-29
Conference PlaceAmsterdam
PublisherSpringer Cham
Abstract

Referring expression grounding represents a complex multimodal task that merits meticulous investigation. To alleviate the conventional methods' reliance on fine-grained supervised data,  there is a pressing need to explore visual grounding techniques under the weakly-supervised setting, encompassing only image-text pairs. Weakly supervised method with pretrained multimodal model has achieved impressive results; however, during the inference phase, it fails to generate a comprehensive attention map for entities, consequently leading to a reduction in inference accuracy. In this study, we introduce Part-aware Prompt Tuning (PPT), an innovative weakly supervised method. By dividing the entities extracted by the detector into different parts to optimize the part-aware prompt during the training phase, these prompt can guide the attention of pretrained multimodal model during the inference phase to obtain a more comprehensive focus on the whole entity, thereby enhancing inference accuracy. Empirical validation on two benchmark datasets, RefCOCO and RefCOCO+, underscores the remarkable superiority of our proposed method over prior referring expression grounding methods.

Sub direction classification其他
planning direction of the national heavy laboratory其他
Paper associated data
Document Type会议论文
Identifierhttp://ir.ia.ac.cn/handle/173211/57464
Collection多模态人工智能系统全国重点实验室_多媒体计算
Corresponding AuthorChangsheng, Xu
Affiliation1.State Key Laboratory of Multimodal Artificial Intelligence Systems(MAIS), Institute of Automation, Chinese Academy of Sciences(CASIA)
2.School of Artificial Intelligence, University of Chinese Academy of Science(UCAS)
3.Damo Academy, Alibaba Group
4.Peng Cheng Laboratory
5.East China Normal University
First Author AffilicationInstitute of Automation, Chinese Academy of Sciences
Corresponding Author AffilicationInstitute of Automation, Chinese Academy of Sciences
Recommended Citation
GB/T 7714
Chenlin, Zhao,Jiabo, Ye,Yaguang, Song,et al. Part-aware Prompt Tuning For Weakly Supervised Referring Expression Grounding[C]:Springer Cham,2024.
Files in This Item: Download All
File Name/Size DocType Version Access License
Part-aware Prompt Tu(6114KB)会议论文 开放获取CC BY-NC-SAView Download
Related Services
Recommend this item
Bookmark
Usage statistics
Export to Endnote
Google Scholar
Similar articles in Google Scholar
[Chenlin, Zhao]'s Articles
[Jiabo, Ye]'s Articles
[Yaguang, Song]'s Articles
Baidu academic
Similar articles in Baidu academic
[Chenlin, Zhao]'s Articles
[Jiabo, Ye]'s Articles
[Yaguang, Song]'s Articles
Bing Scholar
Similar articles in Bing Scholar
[Chenlin, Zhao]'s Articles
[Jiabo, Ye]'s Articles
[Yaguang, Song]'s Articles
Terms of Use
No data!
Social Bookmark/Share
File name: Part-aware Prompt Tuning For Weakly Supervised Referring Expression Grounding.pdf
Format: Adobe PDF
All comments (0)
No comment.
 

Items in the repository are protected by copyright, with all rights reserved, unless otherwise indicated.