Knowledge Commons of Institute of Automation,CAS
CLIP-Driven hierarchical fusion for referring image segmentation | |
Yichen Yan1,2![]() ![]() | |
2024-05 | |
会议名称 | 2024 3rd International Conference on Image, Signal Processing and Pattern Recognition |
会议日期 | 2024/03/08 |
会议地点 | Kunming, China |
摘要 | Referring image segmentation aims to segment an object mentioned in natural language from an image. It is a fundamental computer vision task. This task is challenging because it involves both vision and language features that need to be aligned and fused effectively. For alignment, pre-trained CLIP is widely used in many vision-language tasks for its notable success in aligning these two modalities. However, in the majority of existing methods, vision and language information are independent in the encoder stage, which is a suboptimal fusion approach. In this paper, we introduce an innovative CLIPDriven Hierarchical Fusion framework named CHRIS. We utilize CLIP as the encoder for its valuable vision-language alignment, we also design an effective early fusion approach in the encoder stage called hierarchical attention. Moreover, we introduce a novel hierarchical fusion neck to fuse vision and language information. In this way, the vision and language features contained in CLIP are further fused effectively. We perform comprehensive experiments on the three datasets widely adopted in the research community, RefCOCO, RefCOCO+, and G-Ref. Our proposed framework demonstrates superior performance compared to previous approaches by just using ResNet as the backbone. |
关键词 | Referring Image Segmentation, CLIP, Hierarchical Fusion, Computer Vision |
学科门类 | 工学 |
收录类别 | EI |
语种 | 英语 |
是否为代表性论文 | 否 |
七大方向——子方向分类 | 图像视频处理与分析 |
国重实验室规划方向分类 | 多模态协同认知 |
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/173211/58526 |
专题 | 紫东太初大模型研究中心_图像与视频分析 |
通讯作者 | Jing Liu |
作者单位 | 1.Institute of Automation, Chinese Academy of Sciences 2.School of Artificial Intelligence, 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 | Yichen Yan,Xingjian He,Jing Liu. CLIP-Driven hierarchical fusion for referring image segmentation[C],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 | ||
CHRIS.pdf(5233KB) | 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