A dual-branch adapter module called LCA with contrast maps and pairwise training on a Unity synthetic dataset improves SAM's instance segmentation performance across lighting variations.
Title resolution pending
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cs.CV 2years
2026 2verdicts
UNVERDICTED 2representative citing papers
ModuSeg enables training-free weakly supervised semantic segmentation by explicitly separating geometric object discovery from non-parametric semantic feature retrieval using existing mask proposers and foundation model feature banks.
citing papers explorer
-
Lighting-aware Unified Model for Instance Segmentation
A dual-branch adapter module called LCA with contrast maps and pairwise training on a Unity synthetic dataset improves SAM's instance segmentation performance across lighting variations.
-
ModuSeg: Decoupling Object Discovery and Semantic Retrieval for Training-Free Weakly Supervised Segmentation
ModuSeg enables training-free weakly supervised semantic segmentation by explicitly separating geometric object discovery from non-parametric semantic feature retrieval using existing mask proposers and foundation model feature banks.