Can We Leave Deepfake Data Behind in Training Deepfake Detector? Jikang Cheng

Neural Information Processing Systems 

The generalization ability of deepfake detectors is vital for their applications in real-world scenarios. One effective solution to enhance this ability is to train the models with manually-blended data, which we termed "blendfake", encouraging models to

Similar Docs  Excel Report  more

TitleSimilaritySource
None found