| Benchmark | Model | Rank | Results |
|---|---|---|---|
| image-classification-on-cifar-100 | Swin-L + ML-Decoder | #2 | Percentage correct: 95.1 |
| multi-label-classification-on-ms-coco | ML-Decoder(TResNet-XL, resolution 640) | #2 | mAP: 91.4 |
| multi-label-classification-on-ms-coco | ML-Decoder(TResNet-L, resolution 640) | #5 | mAP: 91.1 |
| multi-label-classification-on-openimages-v6 | TResNet-M | #2 | mAP: 86.8 |
| multi-label-zero-shot-learning-on-nus-wide | ML-Decoder | #3 | mAP: 31.1 |
| fine-grained-image-classification-on-stanford-cars | TResNet-L + ML-Decoder | #4 | Accuracy: 96.41% |