Contextual Transformer Networks for Visual Recognition

Open paper
Benchmark Model Rank Results
image-classification-on-imagenetSE-CoTNetD-152#295Top 1 Accuracy: 84.6%Number of params: 55.8MGFLOPs: 26.5
image-classification-on-imagenetSE-CoTNetD-101#441Top 1 Accuracy: 83.2%Number of params: 40.9MGFLOPs: 8.5
image-classification-on-imagenetSE-CoTNetD-50#603Top 1 Accuracy: 81.6%Number of params: 23.1MGFLOPs: 4.1

Rank counts only results with a code link.