| Benchmark | Model | Rank | Results |
|---|---|---|---|
| zero-shot-cross-modal-retrieval-on-coco-2014 | TIPS-g/14 HR | #4 | Image-to-text R@1: 74.0 |
| zero-shot-cross-modal-retrieval-on-flickr30k | TIPS-SO/14 HR | #4 | Image-to-text R@1: 94.2 |
| zero-shot-cross-modal-retrieval-on-flickr30k | TIPS-g/14 HR | #24 | Text-to-image R@1: 84.5 |
| linear-probe-semantic-segmentation-on-ade20k | TIPS-SO/14 HR + Linear Probe | #6 | mIoU: 49.7 |
| image-classification-on-imagenet | TIPS-g/14 LR (linear probe) | #175 | Top 1 Accuracy: 86.3% |