Boosting Deep Unsupervised Edge Detection via Segment Anything Model

已完结 10 由芳发布于 2024/6/30 23:19:25

DOI:10.1109/TII.2024.3376726
作者：Wenya Yang;Xiao-Diao Chen;Wen Wu;Hongshuai Qin;Kangming Yan;Xiaoyang Mao;Haichuan Song
文献类型：期刊论文
补充材料：只需要正文

Institute of Electrical and Electronics Engineers (IEEE)

Abstract：Segment anything model (SAM), a vision foundation network trained on a massive segmentation corpus, exhibits a superior boundary localization capability for nature images. This work aims to

应助信息

求助已完结，文件已删除 如有需求请重新发布求助一键发布

感谢使用Book学术
本站所有文献仅供个人学习和参考，请勿将文件进行传播。共同遵守网站规定和相关知识产权规定。

上一个求助:其它数据库Naturally Fractured Carbonate Reservoir Characterization: A Case Study of a Mature High-Pour Point Oil Field in Hungary 下一个求助:ElsevierOral exposure of polystyrene microplastics and doxycycline affects mice neurological function via gut microbiota disruption: The orchestrating role of fecal microbiota transplantation