Image Classification on CIFAR-100, ImageNet-O, ImageNet-V2, CIFAR-10
65.27Top-1 AccuracyMulCLIP
Evaluation results
| Method | Links | |
|---|---|---|
| MulCLIPBackbone=ViT-L/14, Fine-tuning dataset=DCI, Evaluation Protocol=zero-shot2025.12 | 65.27 | |
| GOALBackbone=ViT-L/14, Fine-tuning dataset=DOCCI, Evaluation Protocol=zero-shot2025.12 | 65.12 | |
| GOALBackbone=ViT-L/14, Fine-tuning dataset=DCI, Evaluation Protocol=zero-shot2025.12 | 64.69 | |
| MulCLIPBackbone=ViT-L/14, Fine-tuning dataset=DOCCI, Evaluation Protocol=zero-shot2025.12 | 63.07 | |
| MulCLIPBackbone=ViT-B/16, Fine-tuning dataset=DCI, Evaluation Protocol=zero-shot2025.12 | 61.11 | |
| MulCLIPBackbone=ViT-B/16, Fine-tuning dataset=DOCCI, Evaluation Protocol=zero-shot2025.12 | 60.65 | |
| GOALBackbone=ViT-B/16, Fine-tuning dataset=DCI, Evaluation Protocol=zero-shot2025.12 | 59.48 | |
| GOALBackbone=ViT-B/16, Fine-tuning dataset=DOCCI, Evaluation Protocol=zero-shot2025.12 | 58.09 |