Perceptual Grouping in Contrastive Vision-Language Models

Benchmark Model Rank Results
unsupervised-semantic-segmentation-with-language-image-pre-training-on-ade20kCLIPpy ViT-B#10Mean IoU (val): 13.5
unsupervised-semantic-segmentation-with-language-image-pre-training-on-cityscapes-valCLIPpy ViT-B#11mIoU: 18.1