nii-yamagishilab commited on
Commit
217d1a1
·
verified ·
1 Parent(s): 2ec44aa

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +1 -1
README.md CHANGED
@@ -194,7 +194,7 @@ Results shown below can be reproduced using scripts provided in our [GitHub repo
194
  | FakeOrReal | 0.999 | 0.987 | 0.997 | 0.977 | 0.987 | 0.003 | 0.023 | 0.88 @ 0.2488 |
195
  | FakeOrReal-norm | 0.999 | 0.987 | 0.993 | 0.980 | 0.986 | 0.007 | 0.020 | 1.10 @ 0.3834 |
196
  | In-the-Wild | 0.998 | 0.972 | 0.993 | 0.962 | 0.977 | 0.011 | 0.038 | 1.87 @ 0.2462 |
197
- | Deepfake-Eval-2024 | 0.836 | 0.733 | 0.724 | 0.923 | 0.812 | 0.581 | 0.077 | 24.60 @ 0.9970 |
198
 
199
  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.
200
 
 
194
  | FakeOrReal | 0.999 | 0.987 | 0.997 | 0.977 | 0.987 | 0.003 | 0.023 | 0.88 @ 0.2488 |
195
  | FakeOrReal-norm | 0.999 | 0.987 | 0.993 | 0.980 | 0.986 | 0.007 | 0.020 | 1.10 @ 0.3834 |
196
  | In-the-Wild | 0.998 | 0.972 | 0.993 | 0.962 | 0.977 | 0.011 | 0.038 | 1.87 @ 0.2462 |
197
+ | Deepfake-Eval-2024 | 0.807 | 0.739 | 0.747 | 0.909 | 0.820 | 0.581 | 0.091 | 27.54 @ 0.9971 |
198
 
199
  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.
200