Gender Classification on FairFace (test)
87.67Overall AccuracyImage-Text Fusion - T1
Evaluation results
| Method | Links | |||||||||||||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Image-Text Fusion - T1Method Type=Proposed Method, Text Generation Source=BLIP Image-to-Text Model (T1)2025.12 | 87.67 | 85 | 77.036 | 86.615 | 90.168 | 90.704 | 82.438 | 87.894 | 90.723 | 92.743 | 88.89 | 82.449 | 90.588 | 90.82 | 89.512 | 1.204 | 4.22 | — | — | — | — | |
| CLIP - T1Method Type=Baseline, Text Generation Source=BLIP Image-to-Text Model (T1)2025.12 | 87.164 | 80.421 | 80.107 | 81.596 | 92.497 | 88.446 | 84.404 | 87.39 | 90.602 | 92 | 88.384 | 79.184 | 93.823 | 90.285 | 89.72 | 1.185 | 4.817 | — | — | — | — | |
| ITM Guided - T1Method Type=Proposed Method, Text Generation Source=BLIP Image-to-Text Model (T1)2025.12 | 86.642 | 81.536 | 77.704 | 82.883 | 91.203 | 89.376 | 79.948 | 87.768 | 89.277 | 92.5 | 87.626 | 80.136 | 91.323 | 91 | 88.473 | 1.19 | 4.8 | — | — | — | — | |
| Image-Text Fusion - T2Method Type=Proposed Method, Text Generation Source=Attributes (T2)2025.12 | 84.491 | 84.387 | 72.096 | 77.349 | 90.039 | 89.51 | 74.443 | 86.885 | 87 | 91.39 | 84.85 | 78.095 | 90.147 | 89.216 | 84.943 | 1.268 | 6.072 | — | — | — | — | |
| Image OnlyMethod Type=Baseline2025.12 | 84.324 | 89.467 | 64.22 | 79.794 | 87.97 | 88.524 | 83.735 | 88.524 | 83.735 | 92.743 | 78.283 | 81.088 | 83.823 | 89.75 | 82.7 | 1.444 | 7.833 | — | — | — | — | |
| ITM Guided - T2Method Type=Proposed Method, Text Generation Source=Attributes (T2)2025.12 | 84.019 | 80.793 | 73.3 | 73.359 | 90.686 | 87.384 | 80.472 | 83.48 | 89.036 | 90.529 | 86.616 | 74.014 | 90.441 | 88.948 | 85.462 | 1.237 | 6.265 | — | — | — | — | |
| CLIP - T2Method Type=Baseline, Text Generation Source=Attributes (T2)2025.12 | 83.974 | 86.121 | 66.889 | 78.121 | 88.228 | 90.04 | 74.574 | 86.507 | 85.181 | 91.636 | 83.84 | 80.68 | 88.235 | 89.572 | 83.074 | 1.37 | 6.553 | — | — | — | — | |
| FairSAMTest Data=clean2025.03 | 83.94 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | 78.37 | 14.67 | 90.75 | 15.39 | |
| SAMTest Data=clean2025.03 | 82.01 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | 77.27 | 15.18 | 87.81 | 17.32 | |
| TandemNet - T1Method Type=Baseline, Text Generation Source=BLIP Image-to-Text Model (T1)2025.12 | 81.782 | 90.087 | 58.61 | 84.17 | 81.76 | 93.891 | 60.419 | 91.047 | 76.144 | 93.727 | 70.454 | 85.306 | 80.147 | 91.44 | 77.674 | 1.602 | 11.09 | — | — | — | — | |
| TandemNet - T2Method Type=Baseline, Text Generation Source=Attributes (T2)2025.12 | 80.036 | 90.706 | 54.74 | 83.14 | 80.466 | 93.36 | 57.405 | 90.668 | 73.373 | 92.866 | 67.172 | 85.034 | 75.588 | 91.711 | 72.9 | 1.706 | 12.43 | — | — | — | — | |
| MSAMTest Data=clean2025.03 | 79.14 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | 75.49 | 14.7 | 83.59 | 18.86 | |
| GroupSAMTest Data=clean2025.03 | 79.04 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | 75.5 | 12.53 | 83.33 | 14.41 | |
| VanillaTest Data=clean2025.03 | 78 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | 73.96 | 17.04 | 82.96 | 20.08 | |
| GroupDROTest Data=clean2025.03 | 76.18 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | 73.3 | 18.38 | 79.65 | 32.85 |