Semantic Segmentation On Dada Seg

mIoU

Résultats

Résultats de performance de divers modèles sur ce benchmark

Tableau comparatif

Nom du modèle	mIoU
taking-a-closer-look-at-domain-shift-category	28.76
disentangled-non-local-neural-networks	19.7
deep-residual-learning-for-image-recognition	18.96
issafe-improving-semantic-segmentation-in	29.97
differential-treatment-for-stuff-and-things-a	26.85
190807919	27.5
mobilenetv2-inverted-residuals-and-linear	16.05
searching-for-mobilenetv3	18.2
rethinking-semantic-segmentation-from-a	31.8
segformer-simple-and-efficient-design-for	27.0
deep-residual-learning-for-image-recognition	23.60
erfnet-efficient-residual-factorized-convnet	9.0
fda-fourier-domain-adaptation-for-semantic	24.45
exploring-event-driven-dynamic-context-for	32.04
encoder-decoder-with-atrous-separable	26.8
fast-scnn-fast-semantic-segmentation-network	26.32
trans4trans-efficient-transformer-for-1	39.20
rethinking-semantic-segmentation-from-a	30.4
towards-robust-semantic-segmentation-of	46.97
pyramid-scene-parsing-network	20.1
resnest-split-attention-networks	19.99
lawin-transformer-improving-semantic	25.16
bidirectional-learning-for-domain-adaptation	29.66
dual-attention-network-for-scene-segmentation	22.24
in-defense-of-pre-trained-imagenet	20.5
segformer-simple-and-efficient-design-for	16.6
panoptic-feature-pyramid-networks	19.59
segformer-simple-and-efficient-design-for	21.2