Model card
ViT-Adapter-L (BEiT-3).
Microsoft Researchopen-sourceUnknown paramsViT-L with spatial prior adapter + BEiT-3 pre-training + Mask2Former head
ViT-Adapter bridges the gap between plain ViT and hierarchical backbones for dense predictions. BEiT-3 pre-trained ViT-L via ViT-Adapter sets SOTA of 62.8 MS mIoU on ADE20K val. ICLR 2023 Spotlight.
§ 01 · Benchmarks
No recorded benchmark results yet.
This model is in the registry but doesn’t have any benchmark_results rows yet. If you have a score, submit it →
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.
§ 04 · Related models