CaiT-M-36 U 224

Reported on 5 benchmarks across 1 task · 1 paper · 1 SOTA

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

Computer Vision5 results

Image ClassificationonStanford Cars
Accuracy· 2021-03-31
94.2
best: 96.868 (efficient adaptive ensembling)
SOTA
Going deeper with Image Transformers arXiv:2103.17239
Image ClassificationonCIFAR-10
Percentage correct· uses extra data· 2021-03-31
99.4
best: 99.5 (ViT-H/14)
Going deeper with Image Transformers arXiv:2103.17239
Image ClassificationonFlowers-102
Accuracy· uses extra data· 2021-03-31
99.1
best: 99.76 (CCT-14/7x2)
Going deeper with Image Transformers arXiv:2103.17239
Image ClassificationoniNaturalist 2019
Top-1 Accuracy· uses extra data· 2021-03-31
81.8
best: 88.5 (Hiera-H (448px))
Going deeper with Image Transformers arXiv:2103.17239
Image ClassificationonCIFAR-100
Percentage correct· uses extra data· 2021-03-31
93.1
best: 96.08 (EffNet-L2 (SAM))
Going deeper with Image Transformers arXiv:2103.17239