Model card
DINOv2 (ViT-g) + Linear.
Meta AIopen-sourceUnknown paramsSelf-supervised ViT-giant + linear head
Self-supervised vision transformer. 62.0 mIoU on ADE20K with just a linear probe. No fine-tuning needed.
§ 01 · Benchmarks
Every benchmark DINOv2 (ViT-g) + Linear has a recorded score for.
| # | Benchmark | Area · Task | Metric | Value | Rank | Date | Source |
|---|---|---|---|---|---|---|---|
| 01 | ADE20K | Computer Vision · Semantic Segmentation | mIoU | 62.0% | #3 | — | source ↗ |
Rank column shows this model’s position vs all other models scored on the same benchmark + metric (competitors after the slash). #1 in red means current SOTA. Sorted by rank, then newest result.
§ 02 · Strengths by area
Where DINOv2 (ViT-g) + Linear actually performs.
§ 04 · Related models
Other Meta AI models scored on Codesota.
§ 05 · Sources & freshness
Where these numbers come from.
arxiv
1
result
0 of 1 rows marked verified.