OST: Improving Generalization of DeepFake Detection via One-Shot Test-Time Training

Neural Information Processing Systems 

Our key idea is to construct a test-sample-specific auxiliary task to update the model before applying it to the sample. Specifically, we synthesize pseudo-training samples from each test image and create a test-time training objective to update the model.

Similar Docs  Excel Report  more

TitleSimilaritySource
None found