Pyramidal Convolution: Rethinking Convolutional Neural Networks for Visual Recognition

Open paper
Benchmark Model Rank Results
image-classification-on-imagenetPyConvResNet-101#614Top 1 Accuracy: 81.49%Number of params: 42.3M
semantic-segmentation-on-ade20kPyConvSegNet-152#177Validation mIoU: 45.99Test Score: 56.52
semantic-segmentation-on-ade20k-valPyConvSegNet-152#69mIoU: 45.99Pixel Accuracy: 82.49

Rank counts only results with a code link.