Image Quality Assessment on SPAQ 11K (test)
0.93SRCCQ-ALIGN
Evaluation results
| Method | Links | ||
|---|---|---|---|
| Q-ALIGNTraining Set=SPAQ, #Training=8.8K (80%), Evaluation Protocol=Intra-set2023.12 | 0.93 | 0.933 | |
| LIQETraining Set=SPAQ, #Training=8.8K (80%), Evaluation Protocol=Intra-set2023.12 | 0.922 | 0.919 | |
| MUSIQTraining Set=SPAQ, #Training=8.8K (80%), Evaluation Protocol=Intra-set2023.12 | 0.917 | 0.921 | |
| FEWSHOT-Q-ALIGNTraining Set=SPAQ, #Training=2.2K (20%), Evaluation Protocol=Intra-set2023.12 | 0.909 | 0.911 | |
| DBCNNTraining Set=SPAQ, #Training=8.8K (80%), Evaluation Protocol=Intra-set2023.12 | 0.908 | 0.913 | |
| Fang et al.Training Set=SPAQ, #Training=8.8K (80%), Evaluation Protocol=Intra-set2023.12 | 0.908 | 0.909 | |
| NIMATraining Set=SPAQ, #Training=8.8K (80%), Evaluation Protocol=Intra-set2023.12 | 0.907 | 0.91 | |
| Q-ALIGNTraining Set=KonIQ, #Training=7K (70%), Evaluation Protocol=Cross-set2023.12 | 0.887 | 0.886 | |
| CLIP-IQA+Training Set=SPAQ, #Training=8.8K (80%), Evaluation Protocol=Intra-set2023.12 | 0.881 | 0.883 | |
| FEWSHOT-Q-ALIGNTraining Set=KonIQ, #Training=2K (20%), Evaluation Protocol=Cross-set2023.12 | 0.871 | 0.86 | |
| CLIP-IQA+Training Set=KonIQ, #Training=7K (70%), Evaluation Protocol=Cross-set2023.12 | 0.864 | 0.866 | |
| MUSIQTraining Set=KonIQ, #Training=7K (70%), Evaluation Protocol=Cross-set2023.12 | 0.863 | 0.868 | |
| NIMATraining Set=KonIQ, #Training=7K (70%), Evaluation Protocol=Cross-set2023.12 | 0.856 | 0.838 | |
| LIQETraining Set=KonIQ, #Training=7K (70%), Evaluation Protocol=Cross-set2023.12 | 0.833 | 0.846 | |
| DBCNNTraining Set=KonIQ, #Training=7K (70%), Evaluation Protocol=Cross-set2023.12 | 0.806 | 0.812 | |
| HyperIQATraining Set=KonIQ, #Training=7K (70%), Evaluation Protocol=Cross-set2023.12 | 0.788 | 0.791 |