Unsupervised Semantic Segmentation With 4

Mean IoU (val)

النتائج

نتائج أداء النماذج المختلفة على هذا المعيار القياسي

جدول المقارنة

اسم النموذج	Mean IoU (val)
cosmos-cross-modality-self-distillation-for	17.7
tagalign-improving-vision-language-alignment	17.3
ttd-text-tag-self-distillation-enhancing	17.0
groupvit-semantic-segmentation-emerges-from	9.2
reco-retrieve-and-co-segment-for-zero-shot-1	11.2
harnessing-vision-foundation-models-for-high	26.7
proxyclip-proxy-attention-improves-clip-for	24.2
learning-to-generate-text-grounded-mask-for	17.1
ttd-text-tag-self-distillation-enhancing	12.7
denseclip-extract-free-dense-labels-from-clip	9.8
perceptual-grouping-in-vision-language-models	13.5