FastFCN: Rethinking Dilated Convolution in the Backbone for Semantic Segmentation
Open paper
Benchmark
Model
Rank
Results
semantic-segmentation-on-pascal-context
Joint Pyramid Upsampling + EncNet
#37
mIoU: 53.1
semantic-segmentation-on-ade20k
EncNet + JPU
#216
Validation mIoU: 44.34
Test Score: 55.84
Rank counts only results with a code link.