A label-free metric-guided fusion of complementary features from visual foundation models yields consistent gains in dense prediction tasks with improved object semantics and boundary localization.
Despite the additional encoder, through- put remains comparable to single-encoder baselines such as DINOv2-B (1.4 vs
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
-
Metric-Guided Feature Fusion of Visual Foundation Models for Segmentation Tasks
A label-free metric-guided fusion of complementary features from visual foundation models yields consistent gains in dense prediction tasks with improved object semantics and boundary localization.