OVS-DINO structurally aligns DINO with SAM to revitalize attenuated boundary features, achieving SOTA gains of 2.1% average and 6.3% on Cityscapes in weakly-supervised open-vocabulary segmentation.
Title resolution pending
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
years
2026 2verdicts
UNVERDICTED 2representative citing papers
A stage-wise Fourier Neural Operator surrogate predicts per-voxel adjoint gradients to accelerate 3D meta-optics inverse design, replacing expensive FDTD solves with fast inference.
citing papers explorer
-
OVS-DINO: Open-Vocabulary Segmentation via Structure-Aligned SAM-DINO with Language Guidance
OVS-DINO structurally aligns DINO with SAM to revitalize attenuated boundary features, achieving SOTA gains of 2.1% average and 6.3% on Cityscapes in weakly-supervised open-vocabulary segmentation.
-
Neural Adjoint Method for Meta-optics: Accelerating Volumetric Inverse Design via Fourier Neural Operators
A stage-wise Fourier Neural Operator surrogate predicts per-voxel adjoint gradients to accelerate 3D meta-optics inverse design, replacing expensive FDTD solves with fast inference.