Open xarryon opened 1 year ago
It may increase the bounding box regression loss during the training phase. In my experiments, such high regression loss will limit the softmax loss convergence. So I think It may harm the model performance, please check your code and fix this bug~
Actually I just use the code from CADDM without much changes, have you ever encounter this phenomenon?
Thanks for this new deepfake detection work! I tested this project and find the bboxes may bring biases during generation. Does this phenomenon may harm the performance?![image](https://user-images.githubusercontent.com/52477062/227875091-dcf6112e-8ebe-42b8-8d9a-b0c571759ae1.png)