SparseSwin

Reported on 2 benchmarks across 1 task · 1 paper

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

Computer Vision2 results

Image ClassificationonCIFAR-10
Percentage correct· 2023-09-11
97.43
best: 99.5 (ViT-H/14)
SparseSwin: Swin Transformer with Sparse Transformer Block arXiv:2309.05224
Image ClassificationonCIFAR-100
Percentage correct· uses extra data· 2023-09-11
85.35
best: 96.08 (EffNet-L2 (SAM))
SparseSwin: Swin Transformer with Sparse Transformer Block arXiv:2309.05224