Referring Expression Segmentation On Refcoco 3

Overall IoU

Results

Performance results of various models on this benchmark

Comparison Table

Model Name	Overall IoU
vlt-vision-language-transformer-and-query	63.53
referring-image-segmentation-via-cross-modal-1	49.56
universal-segmentation-at-arbitrary	72.70
mask-grounding-for-referring-image	66.16
bi-directional-relationship-inferring-network	48.57
safari-adaptive-sequence-transformer-for	70.78
general-object-foundation-model-for-images	69.6
cross-modal-self-attention-network-for	43.76
lavt-language-aware-vision-transformer-for	62.14
maskris-semantic-distortion-aware-data	70.26
cris-clip-driven-referring-image-segmentation	62.27
universal-instance-perception-as-object	72.47
vision-language-transformer-and-query	55.50
universal-segmentation-at-arbitrary	73.18
polyformer-referring-image-segmentation-as	69.33
gres-generalized-referring-expression-1	66.04
hyperseg-towards-universal-visual	79.0
groundhog-grounding-large-language-models-to	70.5
densely-connected-parameter-efficient-tuning	75.2
mail-a-unified-mask-image-language-trimodal	62.23
maskris-semantic-distortion-aware-data	67.54
see-through-text-grouping-for-referring-image	48.18
comprehensive-multi-modal-interactions-for	52.75
polyformer-referring-image-segmentation-as	67.64
multi-task-visual-grounding-with-coarse-to	74.68
evf-sam-early-vision-language-fusion-for-text	75.2
multi-label-cluster-discrimination-for-visual	79.4
refvos-a-closer-look-at-referring-expressions	44.71
improving-referring-image-segmentation-using	-
hierarchical-open-vocabulary-universal-image-1	73.9
mattnet-modular-attention-network-for	46.67