Understanding Convolution for Semantic Segmentation
Open paper
Benchmark
Model
Rank
Results
semantic-segmentation-on-pascal-voc-2012-test
TuSimple
#18
Mean IoU: 83.1%
semantic-segmentation-on-cityscapes-test
DUC-HDC (ResNet-101)
#58
Mean IoU (class): 77.6%
Rank counts only results with a code link.