MuellerPT pretrains on Lu-Chipman map prediction from Mueller matrices with the MAP-Org dataset, yielding over 20% DICE gain in 5%-label brain segmentation and 8% accuracy gain in 1%-label cancer classification versus scratch baselines.
Journal of the Optical Society of America A13(5), 1106–1113 (1996)
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
MuellerPT: Decomposition Driven Pretraining for Dense Learning in Mueller Polarimetry
MuellerPT pretrains on Lu-Chipman map prediction from Mueller matrices with the MAP-Org dataset, yielding over 20% DICE gain in 5%-label brain segmentation and 8% accuracy gain in 1%-label cancer classification versus scratch baselines.