Skip to content
Snippets Groups Projects
Commit d506769d authored by Rony Abecidan's avatar Rony Abecidan
Browse files

Update README.md

parent 09e74880
No related branches found
No related tags found
No related merge requests found
......@@ -31,7 +31,7 @@ described in the paper. The training relative to the SrcOnly setup is on the lef
**Don't hesitate to click on the gif below to see it better !**
![](https://s10.gifyu.com/images/Adaptation9dfae7fc28cc8ef2.gif)
![](https://s10.gifyu.com/images/Adaptationf80f69ab9e1dfcaa.gif)
- As you can observe, in the **SrcOnly** setup, the forgery detector is more and more prone to false alarms, certainly because compressing images to QF5 results in creating artifacts in the high frequencies that can be misinterpreted by the model. However, it has no real difficulty to identify correctly the forged images.
......
0% Loading or .
You are about to add 0 people to the discussion. Proceed with caution.
Please register or to comment