SmooSeg: smoothness prior for unsupervised semantic segmentation

• المؤلفون الرئيسيون: Lan, Mengcheng, Wang, Xinjiang, Ke, Yiping, Xu, Jiaxing, Feng, Litong, Zhang, Wayne
• مؤلفون آخرون: School of Computer Science and Engineering
• التنسيق: Conference or Workshop Item
• اللغة: English
• منشور في: 2024
• الموضوعات: Engineering::Computer science and engineering::Computing methodologies::Artificial intelligence; Engineering::Computer science and engineering::Computing methodologies::Image processing and computer vision; Unsupervised Semantic Segmentation; Smoothness Prior
• الوصول للمادة أونلاين: https://hdl.handle.net/10356/173324; https://neurips.cc/

Unsupervised semantic segmentation is a challenging task that segments images into semantic groups without manual annotation. Prior works have primarily focused on leveraging prior knowledge of semantic consistency or priori concepts from self-supervised learning methods, which often overlook the co...