nii-yamagishilab commited on
Commit
d8815f6
·
verified ·
1 Parent(s): e2b8920

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +1 -1
README.md CHANGED
@@ -183,7 +183,7 @@ Results shown below can be reproduced using scripts provided in our [GitHub repo
183
  | FakeOrReal | 0.999 | 0.956 | 0.997 | 0.913 | 0.953 | 0.003 | 0.087 | 1.06 @ 0.0430 |
184
  | FakeOrReal-norm | 0.982 | 0.931 | 0.941 | 0.916 | 0.928 | 0.055 | 0.084 | 6.48 @ 0.3893 |
185
  | In-the-Wild | 0.990 | 0.957 | 0.945 | 0.989 | 0.967 | 0.096 | 0.011 | 4.65 @ 0.9497 |
186
- | Deepfake-Eval-2024 | 0.802 | 0.708 | 0.691 | 0.963 | 0.804 | 0.713 | 0.037 | 28.19 @ 0.9991 |
187
 
188
 
189
  You can also fine-tune this model on a specific database, the corresponding code is provided in our [GitHub repository](https://github.com/nii-yamagishilab/AntiDeepfake). Fine-tuning will follow a similar process to training a new model, except that model weights will be initialized as AntiDeepfake checkpoints.
 
183
  | FakeOrReal | 0.999 | 0.956 | 0.997 | 0.913 | 0.953 | 0.003 | 0.087 | 1.06 @ 0.0430 |
184
  | FakeOrReal-norm | 0.982 | 0.931 | 0.941 | 0.916 | 0.928 | 0.055 | 0.084 | 6.48 @ 0.3893 |
185
  | In-the-Wild | 0.990 | 0.957 | 0.945 | 0.989 | 0.967 | 0.096 | 0.011 | 4.65 @ 0.9497 |
186
+ | Deepfake-Eval-2024 | 0.759 | 0.701 | 0.696 | 0.962 | 0.808 | 0.793 | 0.038 | 31.97 @ 0.9995 |
187
 
188
 
189
  You can also fine-tune this model on a specific database, the corresponding code is provided in our [GitHub repository](https://github.com/nii-yamagishilab/AntiDeepfake). Fine-tuning will follow a similar process to training a new model, except that model weights will be initialized as AntiDeepfake checkpoints.