| zero-shot-segmentation-on-ade20k-training-free | COSMOS ViT-B/16 | #1 | mIoU: 17.7 |
| unsupervised-semantic-segmentation-with-language-image-pre-training-on-cityscapes-val | COSMOS ViT-B/16 | #4 | mIoU: 34.7 |
| zero-shot-cross-modal-retrieval-on-flickr30k | COSMOS ViT-B/16 | #5 | Image-to-text R@1: 92.9Image-to-text R@5: 99.4… |
| zero-shot-cross-modal-retrieval-on-flickr30k | COSMOS ViT-B/32 | #13 | Image-to-text R@1: 89.9Image-to-text R@5: 98.8… |
| unsupervised-semantic-segmentation-with-language-image-pre-training-on-ade20k | COSMOS ViT-B/16 | #6 | Mean IoU (val): 17.7 |
| unsupervised-semantic-segmentation-with-language-image-pre-training-on-pascal-context-59 | COSMOS ViT-B/16 | #8 | mIoU: 33.7 |
| unsupervised-semantic-segmentation-with-language-image-pre-training-on-coco-object | COSMOS ViT-B/16 | #9 | mIoU: 31.3 |
| unsupervised-semantic-segmentation-with-language-image-pre-training-on-coco-stuff-171 | COSMOS ViT-B/16 | #9 | mIoU: 23.2 |
| unsupervised-semantic-segmentation-with-language-image-pre-training-on-pascalvoc-20 | COSMOS ViT-B/16 | #10 | mIoU: 77.7 |
| zero-shot-cross-modal-retrieval-on-coco-2014 | COSMOS ViT-B/16 | #15 | Image-to-text R@1: 68.0Image-to-text R@5: 87.8… |
| zero-shot-cross-modal-retrieval-on-coco-2014 | COSMOS ViT-B/32 | #19 | Image-to-text R@1: 64.3Image-to-text R@5: 86.5… |