Collaborative Vision-Text Representation Optimizing for Open-Vocabulary Segmentation

Open paper
Benchmark Model Rank Results
open-vocabulary-panoptic-segmentation-on-ade20kMAFT+#4PQ: 27.1
open-vocabulary-semantic-segmentation-on-1MAFT+#9mIoU: 59.4
open-vocabulary-semantic-segmentation-on-2MAFT+#6mIoU: 36.1
open-vocabulary-semantic-segmentation-on-3MAFT+#6mIoU: 15.1
open-vocabulary-semantic-segmentation-on-5MAFT+#5mIoU: 96.5
open-vocabulary-semantic-segmentation-on-7MAFT+#7mIoU: 21.6

Rank counts only results with a code link.