Knowledge Commons of Institute of Automation,CAS
Part-aware Prompt Tuning For Weakly Supervised Referring Expression Grounding | |
Chenlin, Zhao1,2,3![]() ![]() ![]() | |
2024-01-29 | |
会议名称 | the 30th International Conference on MultiMedia Modeling |
会议日期 | 2024-1-29 |
会议地点 | Amsterdam |
出版者 | Springer Cham |
摘要 | 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. |
七大方向——子方向分类 | 其他 |
国重实验室规划方向分类 | 其他 |
是否有论文关联数据集需要存交 | 否 |
文献类型 | 会议论文 |
条目标识符 | http://ir.ia.ac.cn/handle/173211/57464 |
专题 | 多模态人工智能系统全国重点实验室_多媒体计算 |
通讯作者 | Changsheng, Xu |
作者单位 | 1.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 |
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 | Chenlin, Zhao,Jiabo, Ye,Yaguang, Song,et al. Part-aware Prompt Tuning For Weakly Supervised Referring Expression Grounding[C]:Springer Cham,2024. |
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 | ||
Part-aware Prompt Tu(6114KB) | 会议论文 | 开放获取 | CC BY-NC-SA | 浏览 下载 |
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。
修改评论