| image-classification-on-oxford-iiit-pets | NNCLR | #3 | Accuracy: 91.8 |
| fine-grained-image-classification-on-birdsnap | NNCLR | #5 | Accuracy: 61.4% |
| fine-grained-image-classification-on-sun397 | NNCLR | #5 | Accuracy: 62.5 |
| image-classification-on-food-101 | NNCLR | #6 | Accuracy (%): 76.7 |
| fine-grained-image-classification-on-caltech-101 | NNCLR | #9 | Top-1 Error Rate: 8.7% |
| image-classification-on-dtd | NNCLR | #10 | Accuracy: 75.5 |
| image-classification-on-stanford-cars | NNCLR | #21 | Accuracy: 67.1 |
| semi-supervised-image-classification-on-imagenet-10-labeled-data | NNCLR (ResNet-50) | #35 | Top 1 Accuracy: 69.8%Top 5 Accuracy: 89.3 |
| semi-supervised-image-classification-on-imagenet-1-labeled-data | NNCLR (ResNet-50) | #39 | Top 1 Accuracy: 56.4%Top 5 Accuracy: 80.7 |
| fine-grained-image-classification-on-fgvc-aircraft | NNCLR | #43 | Accuracy: 64.1 |
| image-classification-on-flowers-102 | NNCLR | #51 | Accuracy: 95.1 |
| self-supervised-image-classification-on-imagenet | NNCLR (ResNet-50, multi-crop) | #64 | Top 1 Accuracy: 75.6%Top 5 Accuracy: 92.4Number of Params: 25M |
| image-classification-on-cifar-100 | NNCLR | #165 | Percentage correct: 79 |
| image-classification-on-cifar-10 | NNCLR | #199 | Percentage correct: 93.7 |