SegGPT: Segmenting Everything In Context

Benchmark Model Rank Results
few-shot-semantic-segmentation-on-coco-20i-5-shotSegGPT (ViT)#1Mean IoU: 67.9
few-shot-semantic-segmentation-on-pascal-5i-1-shotSegGPT (ViT)#1Mean IoU: 83.2
few-shot-semantic-segmentation-on-pascal-5i-5-shotSegGPT (ViT)#1Mean IoU: 89.8
few-shot-semantic-segmentation-on-coco-20i-1-shotSegGPT (ViT)#2Mean IoU: 56.1
semi-supervised-video-object-segmentation-on-youtube-vos-2018-validation-official-serverSegGPT (extra data)#6J&F: 74.7
few-shot-semantic-segmentation-on-fss-1000-5-shotSegGPT (ViT)#10Mean IoU: 89.3
few-shot-semantic-segmentation-on-fss-1000-1-shotSegGPT (ViT)#21Mean IoU: 85.6
semi-supervised-video-object-segmentation-on-moseSegGPT (extra data)#23J&F: 45.1