Segment scene unsupervised using close features have similar semantics with SmooSeg
Segment scene unsupervised using close features have similar semantics with SmooSeg
SmooSeg: Smoothness Prior for Unsupervised Semantic Segmentation
arXiv paper abstract https://arxiv.org/abs/2310.17874
arXiv PDF paper https://arxiv.org/pdf/2310.17874.pdf
Unsupervised semantic segmentation is a challenging task that segments images into semantic groups without manual annotation.
Prior works ... leveraging prior knowledge of semantic consistency or priori concepts from self-supervised learning methods, which ... overlook the coherence ... of image segments.
... demonstrate that the smoothness prior, asserting that close features in a metric space share the same semantics, can significantly simplify segmentation by casting unsupervised semantic segmentation as an energy minimization problem.
... propose a novel approach called SmooSeg that harnesses self-supervised learning methods to model the closeness relationships among observations as smoothness signals.
... introduce a novel smoothness loss that promotes piecewise smoothness within segments while preserving discontinuities across different segments.
... SmooSeg significantly outperforms STEGO in terms of pixel accuracy ...
Please like and share this post if you enjoyed it using the buttons at the bottom!
Stay up to date. Subscribe to my posts https://morrislee1234.wixsite.com/website/contact
Web site with my other posts by category https://morrislee1234.wixsite.com/website
Commentaires