Noisy Student Training when you have 100 hours labelled and 60,000 unlabelled
How the noisy student loop actually works, why the noise and the pseudo-label filter are the method, and where it falls apart in practice.
2 posts
How the noisy student loop actually works, why the noise and the pseudo-label filter are the method, and where it falls apart in practice.
Why combining CNNs, InceptionNeXt, and a Vision Transformer beat either alone for video deepfake detection — and why cross-dataset generalization is the metric that matters.