GroupViT: Semantic Segmentation Emerges from Text Supervision

Benchmark Model Rank Results
unsupervised-semantic-segmentation-with-language-image-pre-training-on-ade20kGroupViT (RedCaps)#13Mean IoU (val): 9.2
unsupervised-semantic-segmentation-with-language-image-pre-training-on-coco-objectGroupViT (RedCaps)#9mIoU: 27.5
unsupervised-semantic-segmentation-with-language-image-pre-training-on-coco-stuff-171GroupViT#12mIoU: 11.1
unsupervised-semantic-segmentation-with-language-image-pre-training-on-pascal-context-59GroupViT (RedCaps)#11mIoU: 23.4
unsupervised-semantic-segmentation-with-language-image-pre-training-on-pascalvoc-20GroupViT (RedCaps)#7mIoU: 79.7