Wider or Deeper: Revisiting the ResNet Model for Visual Recognition
Open paper
Benchmark
Model
Rank
Results
semantic-segmentation-on-cityscapes
ResNet-38
#54
Mean IoU (class): 78.4%
semantic-segmentation-on-pascal-context
ResNet-38
#44
mIoU: 48.1
semantic-segmentation-on-pascal-voc-2012
ResNet-38 MS COCO
#10
Mean IoU: 84.9%
Rank counts only results with a code link.