AutoFormer-S | 384

Reported on 3 benchmarks across 2 tasks · 1 paper · 2 SOTA

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

Computer Vision3 results

Image ClassificationonOxford 102 Flowers
Top 1 Accuracy· 2021-07-01
98.8
SOTA
AutoFormer: Searching Transformers for Visual Recognition arXiv:2107.00651
Fine-Grained Image ClassificationonOxford 102 Flowers
Top 1 Accuracy· 2021-07-01
98.8
SOTA
AutoFormer: Searching Transformers for Visual Recognition arXiv:2107.00651
Image ClassificationonCIFAR-10
Percentage correct· uses extra data· 2021-07-01
99.1
best: 99.5 (ViT-H/14)
AutoFormer: Searching Transformers for Visual Recognition arXiv:2107.00651