nii-yamagishilab commited on
Commit
7928e11
·
verified ·
1 Parent(s): a77f7f4

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 | 0.980 | 0.962 | 0.999 | 0.980 | 0.038 | 0.001 | 1.40 @ 0.8584 |
195
  | FakeOrReal-norm | 0.982 | 0.858 | 0.775 | 1.000 | 0.873 | 0.278 | 0.000 | 5.92 @ 0.9861 |
196
  | In-the-Wild | 0.996 | 0.973 | 0.979 | 0.978 | 0.979 | 0.036 | 0.022 | 2.90 @ 0.6236 |
197
- | Deepfake-Eval-2024 | 0.789 | 0.726 | 0.724 | 0.904 | 0.804 | 0.570 | 0.096 | 27.72 @ 0.9919 |
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 | 0.980 | 0.962 | 0.999 | 0.980 | 0.038 | 0.001 | 1.40 @ 0.8584 |
195
  | FakeOrReal-norm | 0.982 | 0.858 | 0.775 | 1.000 | 0.873 | 0.278 | 0.000 | 5.92 @ 0.9861 |
196
  | In-the-Wild | 0.996 | 0.973 | 0.979 | 0.978 | 0.979 | 0.036 | 0.022 | 2.90 @ 0.6236 |
197
+ | Deepfake-Eval-2024 | 0.742 | 0.726 | 0.741 | 0.893 | 0.810 | 0.590 | 0.107 | 32.84 @ 0.9938 |
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