PhraseCut

ImagesTextsIntroduced 2020-05-19

PhraseCut is a dataset consisting of 77,262 images and 345,486 phrase-region pairs. The dataset is collected on top of the Visual Genome dataset and uses the existing annotations to generate a challenging set of referring phrases for which the corresponding regions are manually annotated.

Source: PhraseCut: Language-based Image Segmentation in the Wild Image Source: https://people.cs.umass.edu/~chenyun/publication/phrasecut/

Benchmarks

Instance Segmentation/Mean IoU Instance Segmentation/Pr@0.5 Instance Segmentation/Pr@0.7 Instance Segmentation/Pr@0.9 Referring Expression Segmentation/Mean IoU Referring Expression Segmentation/Pr@0.5 Referring Expression Segmentation/Pr@0.7 Referring Expression Segmentation/Pr@0.9