SIT-HSS builds a pixel graph whose radius is chosen by 1D structural entropy, then greedily merges adjacent clusters by 2D structural entropy to form superpixels, outperforming nine baselines on BSDS500, SBD, and PASCAL-S.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Hierarchical Superpixel Segmentation via Structural Information Theory
SIT-HSS builds a pixel graph whose radius is chosen by 1D structural entropy, then greedily merges adjacent clusters by 2D structural entropy to form superpixels, outperforming nine baselines on BSDS500, SBD, and PASCAL-S.