TransNeXt-Base (IN-1K pretrain, Mask2Former, 512)

Reported on 4 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.

Medical2 results

Semantic SegmentationonADE20K
Params (M)· 2023-11-28
109
best: 3000 (FD-SwinV2-G)
TransNeXt: Robust Foveal Visual Perception for Vision Transformers arXiv:2311.17132
Semantic SegmentationonADE20K
Validation mIoU· 2023-11-28
54.7
best: 63.6 (ViT-P (InternImage-H))
TransNeXt: Robust Foveal Visual Perception for Vision Transformers arXiv:2311.17132

Audio2 results

10-shot image generationonADE20K
Params (M)· 2023-11-28
109
best: 3000 (FD-SwinV2-G)
TransNeXt: Robust Foveal Visual Perception for Vision Transformers arXiv:2311.17132
10-shot image generationonADE20K
Validation mIoU· 2023-11-28
54.7
best: 63.6 (ViT-P (InternImage-H))
TransNeXt: Robust Foveal Visual Perception for Vision Transformers arXiv:2311.17132