FreeSeg: Unified, Universal and Open-Vocabulary Image Segmentation | |
Jie Qin1,2,3; Jie Wu2; Pengxiang Yan2; Ming Li2; Ren Yuxi2; Xuefeng Xiao2; Yitong Wang2; Rui Wang2; Shilei Wen2; Xin Pan2 | |
2023 | |
会议日期 | 6.18-6.22 |
会议地点 | 加拿大温哥华市 |
英文摘要 | Recently, open-vocabulary learning has emerged to accomplish segmentation for arbitrary categories of text-based descriptions, which popularizes the segmentation system to more general-purpose application scenarios. However, existing methods devote to designing specialized architectures or parameters for specific segmentation tasks. These customized design paradigms lead to fragmentation between various segmentation tasks, thus hindering the uniformity of segmentation models. Hence in this paper, we propose FreeSeg, a generic framework to accomplish Unified, Universal and Open-Vocabulary Image Segmentation. FreeSeg optimizes an all-in-one network via one-shot training and employs the same architecture and parameters to handle diverse segmentation tasks seamlessly in the inference procedure. |
内容类型 | 会议论文 |
源URL | [http://ir.ia.ac.cn/handle/173211/57147] |
专题 | 精密感知与控制研究中心_精密感知与控制 |
作者单位 | 1.Institute of Automation, Chinese Academy of Sciences 2.ByteDance Inc 3.School of Artificial Intelligence, University of Chinese Academy of Sciences |
推荐引用方式 GB/T 7714 | Jie Qin,Jie Wu,Pengxiang Yan,et al. FreeSeg: Unified, Universal and Open-Vocabulary Image Segmentation[C]. 见:. 加拿大温哥华市. 6.18-6.22. |
个性服务 |
查看访问统计 |
相关权益政策 |
暂无数据 |
收藏/分享 |
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