CoAtNet-1

Reported on 4 benchmarks across 1 task · 1 paper · 2 SOTA

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

Computer Vision4 results

Image ClassificationonGasHisSDB
Accuracy· 2021-06-09
98.74
SOTA
CoAtNet: Marrying Convolution and Attention for All Data Sizes arXiv:2106.04803
Image ClassificationonGasHisSDB
F1-Score· 2021-06-09
99.38
SOTA
CoAtNet: Marrying Convolution and Attention for All Data Sizes arXiv:2106.04803
Image ClassificationonGasHisSDB
Precision· 2021-06-09
99.97
CoAtNet: Marrying Convolution and Attention for All Data Sizes arXiv:2106.04803
Image ClassificationonImageNet
GFLOPs· 2021-06-09
8.4
best: 1478 (InternImage-H)
CoAtNet: Marrying Convolution and Attention for All Data Sizes arXiv:2106.04803