OCNet: Object Context Network for Scene Parsing
Open paper
Benchmark
Model
Rank
Results
semantic-segmentation-on-trans10k
OCNet
#9
mIoU: 66.31%
GFLOPs: 43.31
semantic-segmentation-on-cityscapes-test
OCNet
#33
Mean IoU (class): 81.7%
Rank counts only results with a code link.