Hello, may I ask how to configure using your own dataset

Thank you for sharing your code, I want to ask :
ModuleNotFoundError: No module named 'tools.eval_utils' ?

Maybe miss some code?

Hi,

Thank you for sharing your excellent work and code. It's been very insightful, but I've encountered a couple of issues regarding the implementation that I hope you can help clarify:

1. Necessity of the Classifier in Figure 2: Is the Classifier shown in Figure 2 of your paper essential for the model to function effectively? Specifically, if I work exclusively with a tampered dataset, could the Classifier be omitted? I presume that the system might still perform adequately without it, but I would appreciate your insight on this matter.

2. Training with Only Tampered Images: In my experimental setup, I use only tampered images to train the model, fine-tuning it based on your casiav2_ep40_lr2.5e-4.pth. However, the loss behavior is puzzling; it decreases to 2.0794 and then plateaus, showing no further decrease. I have set LAMBDA_CLS to 0.0 to negate the Classifier's impact. What could be the possible reasons for this? I have tested it on two different datasets and observed consistent results.

Hi authors!

Thanks for your outstanding work.

However, after running an evaluation script on the CASIAv1 dataset with your official checkpoint trained with CASIAv2, we found that the F1 score is 0.1918. After carefully checking the code I can not find any clues about these unexpected results.

Detailly, I implemented the F1 metrics with the third mask returned from your nn.Modules class.

Here are the visualizing results on CASIAv1:

Do you have any ideas about it? Any help is sincerely appreciated! Thank you very much.

Hi, in your paper you mention that you perform high frequency feature extraction with the DCT transform, however I cannot find this implementation in the repo. Where is it performed?
Thanks