Transformer Meets Convolution: A Bilateral Awareness Network for Semantic Segmentation of Very Fine Resolution Urban Scene Images

Open paper

Benchmark	Model	Rank	Results
semantic-segmentation-on-isprs-vaihingen	BANet	#8	Overall Accuracy: 90.5
semantic-segmentation-on-uavid	BANet	#8	Mean IoU: 64.6
semantic-segmentation-on-isprs-potsdam	BANet	#11	Overall Accuracy: 91.06