Vision-Aware Text Features in Referring Image Segmentation: From Object Understanding to Context Understanding

Benchmark Model Rank Results
referring-video-object-segmentation-on-refer-youtube-vosVATEX#9J&F: 65.4J: 63.3F: 67.5
referring-expression-segmentation-on-refcoco-testaVATEX#12mIoU: 79.64
referring-expression-segmentation-on-refcoco-testbVATEX#12mIoU: 75.64
referring-expression-segmentation-on-davis-2017-valVATEX#15J&F score: 65.4
referring-expression-segmentation-on-refcocog-testVATEX#17mIoU: 70.58
referring-expression-segmentation-on-refcocog-valVATEX#24IoU: 0.7554mIoU: 69.73
referring-expression-segmentation-on-refcoco-plus-test-bVATEX#26mIoU: 62.52
referring-expression-segmentation-on-refcoco-plus-testaVATEX#29mIoU: 74.41
referring-expression-segmentation-on-refcoco-plus-valVATEX#34Mean IoU: 70.02
referring-expression-segmentation-on-refcoco-valVATEX#38mIoU: 78.16