MapSR achieves 59.64% mIoU on land cover super-resolution from low-resolution labels alone by prompting frozen vision foundation models and applying training-free inference plus graph refinement.
Upsampling DINOv2 features for unsupervised vision tasks and weakly supervised materials segmentation
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
PANC augments Normalized Cut with anchor-augmented token graphs using priors to steer spectral partitions, yielding mIoU gains of 2.3-8.7% over baselines on DUTS-TE, DUT-OMRON, and CrackForest.
citing papers explorer
-
MapSR: Prompt-Driven Land Cover Map Super-Resolution via Vision Foundation Models
MapSR achieves 59.64% mIoU on land cover super-resolution from low-resolution labels alone by prompting frozen vision foundation models and applying training-free inference plus graph refinement.
-
PANC: Prior-Aware Normalized Cut via Anchor-Augmented Token Graphs
PANC augments Normalized Cut with anchor-augmented token graphs using priors to steer spectral partitions, yielding mIoU gains of 2.3-8.7% over baselines on DUTS-TE, DUT-OMRON, and CrackForest.