FreeSeg: Unified, Universal and Open-Vocabulary Image Segmentation

Jie Qin; Jie Wu; Pengxiang Yan; Ming Li; Yuxi Ren; Xuefeng Xiao; Yitong Wang; Rui Wang; Shilei Wen; Xin Pan; Xingang Wang

doi:10.1109/cvpr52729.2023.01863

CVPR2023顶会

FreeSeg: Unified, Universal and Open-Vocabulary Image Segmentation

Jie Qin, Jie Wu, Pengxiang Yan, Ming Li, Yuxi Ren, Xuefeng Xiao, Yitong Wang, Rui Wang, Shilei Wen, Xin Pan, Xingang Wang

DOI 出版方

2023年份

50顶会引用

摘要

Figure 1. We propose FreeSeg, a generic framework to accomplish Unified, Universal and Open-Vocabulary Image Segmentation. (a) FreeSeg optimizes an all-in-one network via one-shot training. (b) FreeSeg employs the same architecture and parameters to handle diverse segmentation tasks seamlessly in the inference procedure. (c) FreeSeg establishes new state-of-the-art performance across diverse segmentation tasks, training datasets and zero-shot generalization.