CvT-W24

Reported on 4 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 Vision4 results

Image ClassificationonFlowers-102
Accuracy· uses extra data· 2021-03-29
99.72
best: 99.76 (CCT-14/7x2)
SOTA
CvT: Introducing Convolutions to Vision Transformers arXiv:2103.15808
Image ClassificationonCIFAR-10
Percentage correct· uses extra data· 2021-03-29
99.39
best: 99.5 (ViT-H/14)
CvT: Introducing Convolutions to Vision Transformers arXiv:2103.15808
Image ClassificationonOxford-IIIT Pets
Accuracy· 2021-03-29
94.73
best: 97.1 (EffNet-L2 (SAM))
CvT: Introducing Convolutions to Vision Transformers arXiv:2103.15808
Image ClassificationonCIFAR-100
Percentage correct· uses extra data· 2021-03-29
94.09
best: 96.08 (EffNet-L2 (SAM))
CvT: Introducing Convolutions to Vision Transformers arXiv:2103.15808