Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentation

Benchmark Model Rank Results
semantic-segmentation-on-bdd100k-valDeeplabv3+#4mIoU: 63.6
semantic-segmentation-on-bjroadDeepLabv3+#8IoU: 50.81
semantic-segmentation-on-cityscapes-valDeepLabv3+ (Dilated-Xception-71)#53mIoU: 79.6
semantic-segmentation-on-dada-segDeepLabV3+ (ACDC)#12mIoU: 26.8
semantic-segmentation-on-densepassDeepLabV3+ (ResNet-101)#21mIoU: 32.5%
semantic-segmentation-on-eventscapeDeepLabV3+#6mIoU: 53.65
semantic-segmentation-on-fine-grained-grassDeepLabv3+#7mIoU: 47.95
semantic-segmentation-on-mcubesDeepLabV3+ (RGB-A-D-N)#20mIoU: 38.13%
semantic-segmentation-on-pascal-voc-2012DeepLabv3+ (Xception-65-JFT)#1Mean IoU: 89.0%
semantic-segmentation-on-pascal-voc-2012DeepLabv3+ (Xception-JFT)#2Mean IoU: 89.0%
semantic-segmentation-on-pascal-voc-2012-valDeepLabV3+ (ResNet-101)#24mIoU (Syn): 75.39
semantic-segmentation-on-skyscapes-dense-1DeepLabv3+#1Mean IoU: 38.20
semantic-segmentation-on-synpassDeepLabv3+#5mIoU: 29.66%
semantic-segmentation-on-trans10kDeepLabV3+#5mIoU: 68.87%GFLOPs: 37.98
semantic-segmentation-on-urbanlfDeepLabV3+ (ResNet-101)#14mIoU (Real): 76.27
semantic-segmentation-on-vaihingenDeepLabV3+#12mIoU: 72.90