Open Vocabulary Semantic Segmentation On 1

mIoU

평가 결과

이 벤치마크에서 각 모델의 성능 결과

비교 표

모델 이름	mIoU
learning-to-generate-text-grounded-mask-for	33.9
open-vocabulary-semantic-segmentation-with-2	50.1
tagalign-improving-vision-language-alignment	37.6
mask-adapter-the-devil-is-in-the-masks-for	60.4
convolutions-die-hard-open-vocabulary-1	58.4
collaborative-vision-text-representation	59.4
learning-mask-aware-clip-representations-for	58.5
cat-seg-cost-aggregation-for-open-vocabulary	63.3
open-vocabulary-semantic-segmentation-with	55.7
sed-a-simple-encoder-decoder-for-open	60.6
in-defense-of-lazy-visual-grounding-for-open	34.7
hyperseg-towards-universal-visual	64.6
ttd-text-tag-self-distillation-enhancing	37.4
2112-14757	47.7
silc-improving-vision-language-pretraining	63.5
open-vocabulary-panoptic-segmentation-with	45.9
open-vocabulary-semantic-segmentation-with-4	60.2
clip-surgery-for-better-explainability-with	29.3
maskclip-a-mask-based-clip-fine-tuning	62.5
open-vocabulary-segmentation-with-semantic	59.3
ttd-text-tag-self-distillation-enhancing	31.0
clipself-vision-transformer-distills-itself	62.3
open-vocabulary-panoptic-segmentation-with-1	57.3