DepthMatch (DINOv2-S)

Reported on 2 benchmarks across 2 tasks · 1 paper

Note: results are matched by exact model name. Different papers may use the same name for different model variants.

Medical1 result

Semantic SegmentationonNYU Depth v2
Mean IoU· uses extra data· 2025-05-26
61.4
best: 63.6 (OmniVec2)
DepthMatch: Semi-Supervised RGB-D Scene Parsing through Depth-Guided Regularization arXiv:2505.20041

Audio1 result

10-shot image generationonNYU Depth v2
Mean IoU· uses extra data· 2025-05-26
61.4
best: 63.6 (OmniVec2)
DepthMatch: Semi-Supervised RGB-D Scene Parsing through Depth-Guided Regularization arXiv:2505.20041