Groups
Category
Level
Stochastic Depth randomly drops whole residual layers during training while keeping the full network at inference time.
Early stopping halts training when the validation loss stops improving, preventing overfitting and saving compute.
Label smoothing replaces a hard one-hot target with a slightly softened distribution to reduce model overconfidence.
Dropout randomly turns off (zeros) some neurons during training to prevent the network from memorizing the training data.