Image Classification on DomainNet (ID and OOD Metrics)
72.54ID AccuracyManually Annotated
Evaluation results
| Method | Links | ||
|---|---|---|---|
| Manually AnnotatedType=Training-dependent, Pre-trained model=CLIP vision encoder2024.03 | 72.54 | 19.09 | |
| LE + CONANType=Training-dependent, Pre-trained model=CLIP vision encoder2024.03 | 54.6 | 15.62 | |
| HIRPG + CONANType=Training-dependent, Pre-trained model=CLIP vision encoder2024.03 | 51.85 | 21.01 | |
| CHB + CONANType=Training-dependent, Pre-trained model=CLIP vision encoder2024.03 | 49.17 | 15.51 | |
| HIRPGType=Training-dependent, Pre-trained model=CLIP vision encoder2024.03 | 46.19 | 17.8 | |
| SC + CONANType=Training-dependent, Pre-trained model=CLIP vision encoder2024.03 | 44.66 | 12.01 | |
| LEType=Training-dependent, Pre-trained model=CLIP vision encoder2024.03 | 40.74 | 10.47 | |
| CHBType=Training-dependent, Pre-trained model=CLIP vision encoder2024.03 | 35.97 | 9.6 | |
| CCG + CONANType=Training-dependent, Pre-trained model=CLIP vision encoder2024.03 | 32.31 | 8.72 | |
| SCType=Training-dependent, Pre-trained model=CLIP vision encoder2024.03 | 30.42 | 8.23 | |
| Glide-synType=Training-dependent, Pre-trained model=CLIP vision encoder2024.03 | 29.02 | 6.73 | |
| CCGType=Training-dependent, Pre-trained model=CLIP vision encoder2024.03 | 26.59 | 6.89 | |
| SuS-X-SDType=Training-free, Pre-trained model=YFCC100M ResNet50-CLIP2024.03 | 20.06 | 7.5 | |
| CuPLType=Training-free, Pre-trained model=YFCC100M ResNet50-CLIP2024.03 | 18.25 | 6.36 | |
| VisDescType=Training-free, Pre-trained model=YFCC100M ResNet50-CLIP2024.03 | 16.87 | 6.52 | |
| CALIPType=Training-free, Pre-trained model=YFCC100M ResNet50-CLIP2024.03 | 16.43 | 6.39 | |
| CLIP-ZSType=Training-free, Pre-trained model=YFCC100M ResNet50-CLIP2024.03 | 14.69 | 5.17 | |
| SD-ClfType=Training-free, Pre-trained model=YFCC100M ResNet50-CLIP2024.03 | 12.27 | 11.85 |