Understanding how and why data distillation methods work is vital not only for improving these methods but also for revealing fundamental characteristics of "good" training data.

D.9 Parameter Size and Inference Speed . . . . . . . . . . . . . . . . . . . . . . . .

If the required memory to train a model exceeds this limit, the device will be excluded from the training.

We assume that training data is available to describe only the inlier distribution. Recent approaches primarily leverage deep encoder-decoder network architectures to compute a reconstruction error that is used to either compute a novelty score or to train a one-class classifier.

The OOD results quoted in the papers use a range of classification network architectures.

We trained ResNet-50, for 1.1m iterations. We used an SGD optimizer, with a 0.03 learning rate,32 batch size,0.9