LLISE is a Locally Linear Embedding variant that uses an SSIM-based distance instead of squared error and is reported to separate image distortion types better than LLE.
IEEE signal processing magazine 26(1) (2009) 98–117
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
stat.ML 1years
2019 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Locally Linear Image Structural Embedding for Image Structure Manifold Learning
LLISE is a Locally Linear Embedding variant that uses an SSIM-based distance instead of squared error and is reported to separate image distortion types better than LLE.