Res-SAM uses SAM click prompts to propose candidate anomaly regions, then refines and classifies them with reservoir-computed wave-dynamics features, reporting detection accuracy above 85% on a 626-frame GPR dataset.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
eess.IV 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Reservoir-enhanced Segment Anything Model for Subsurface Diagnosis
Res-SAM uses SAM click prompts to propose candidate anomaly regions, then refines and classifies them with reservoir-computed wave-dynamics features, reporting detection accuracy above 85% on a 626-frame GPR dataset.