Swin-L

Reported on 3 benchmarks across 3 tasks · 2 papers

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

Medical1 result

Semantic SegmentationonADE20K
Validation mIoU· 2023-01-02
53.5
best: 63.6 (ViT-P (InternImage-H))
ConvNeXt V2: Co-designing and Scaling ConvNets with Masked Autoencoders arXiv:2301.00808

Audio1 result

10-shot image generationonADE20K
Validation mIoU· 2023-01-02
53.5
best: 63.6 (ViT-P (InternImage-H))
ConvNeXt V2: Co-designing and Scaling ConvNets with Masked Autoencoders arXiv:2301.00808

Computer Vision1 result

Image ClassificationonImageNet
GFLOPs· 2021-03-25
103.9
best: 1478 (InternImage-H)
Swin Transformer: Hierarchical Vision Transformer using Shifted Windows arXiv:2103.14030