Weakly Supervised Co-training with Swapping Assignments for Semantic Segmentation

Open paper
Benchmark Model Rank Results
weakly-supervised-semantic-segmentation-on-coco-2014-valCoSA (SWIN-B, multi-stage)#5mIoU: 53.7
weakly-supervised-semantic-segmentation-on-coco-2014-valCoSA (ViT-B, single-stage)#6mIoU: 51.1
weakly-supervised-semantic-segmentation-on-pascal-voc-2012-valCoSA (SWIN-B, multi-stage)#4Mean IoU: 81.4
weakly-supervised-semantic-segmentation-on-pascal-voc-2012-valCoSA (ViT-B, single-stage)#8Mean IoU: 76.4

Rank counts only results with a code link.