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

Benchmark Model Rank Results
referring-expression-segmentation-on-davisVATEX#15J&F score: 65.4
referring-expression-segmentation-on-refcocoVATEX#32mIoU: 78.16
referring-expression-segmentation-on-refcoco-3VATEX#28Mean IoU: 70.02
referring-expression-segmentation-on-refcoco-4VATEX#25mIoU: 74.41
referring-expression-segmentation-on-refcoco-5VATEX#25mIoU: 62.52
referring-expression-segmentation-on-refcoco-8VATEX#12mIoU: 79.64
referring-expression-segmentation-on-refcoco-9VATEX#12mIoU: 75.64
referring-expression-segmentation-on-refcocogVATEX#21IoU: 0.7554mIoU: 69.73
referring-expression-segmentation-on-refcocog-1VATEX#16mIoU: 70.58
referring-video-object-segmentation-on-referVATEX#8J&F: 65.4J: 63.3F: 67.5