Context Contrasted Feature and Gated Multi-Scale Aggregation for Scene Segmentation
Open paper
Benchmark
Model
Rank
Results
semantic-segmentation-on-coco-stuff-test
CCL (ResNet-101)
#17
mIoU: 35.7%
semantic-segmentation-on-sun-rgbd
EMSANet (2x ResNet-34 NBt1D, PanopticNDT version, finetuned)
#37
Mean IoU: 47.1%
Rank counts only results with a code link.