| image-classification-on-vtab-1k | ALIGN (50 hypers/task) | #1 | Top-1 Accuracy: 79.99 |
| fine-grained-image-classification-on-food-101 | ALIGN | #3 | Accuracy: 95.88 |
| fine-grained-image-classification-on-oxford-iiit-pet | ALIGN | #3 | Accuracy: 96.19% |
| fine-grained-image-classification-on-stanford-cars | ALIGN | #5 | Accuracy: 96.13% |
| cross-modal-retrieval-on-flickr30k | ALIGN | #8 | Image-to-text R@1: 95.3Image-to-text R@5: 99.8Image-to-text R@10: 100… |
| zero-shot-transfer-image-classification-on-imagenet-v2 | ALIGN | #8 | Accuracy (Private): 70.1 |
| image-classification-on-flowers-102 | ALIGN | #9 | Accuracy: 99.65% |
| zero-shot-transfer-image-classification-on-imagenet-r | ALIGN | #10 | Accuracy: 92.2 |
| zero-shot-transfer-image-classification-on-imagenet | ALIGN | #12 | Accuracy (Private): 76.4 |
| zero-shot-transfer-image-classification-on-imagenet-a | ALIGN | #13 | Accuracy (Private): 75.8 |
| cross-modal-retrieval-on-coco-2014 | ALIGN | #14 | Text-to-image R@1: 59.9Text-to-image R@5: 83.3… |
| zero-shot-cross-modal-retrieval-on-flickr30k | ALIGN | #16 | Image-to-text R@1: 88.6Image-to-text R@5: 98.7… |
| zero-shot-cross-modal-retrieval-on-coco-2014 | ALIGN | #22 | Image-to-text R@1: 58.6Image-to-text R@5: 83.0… |
| image-classification-on-imagenet | ALIGN (EfficientNet-L2) | #38 | Top 1 Accuracy: 88.64%Number of params: 480M |
| image-classification-on-imagenet-v2 | ALIGN (extra data) | #38 | Top 1 Accuracy: 70.1 |