The work shows that i) a simple ensemble of independently trained networks performs significantly better than recent techniques ii) a simple test-time augmentation applied to a conventional network outperforms low-parameters ensembles (e.g. Dropout) and also improves all ensembles for free iii) a comparison of the uncertainty estimation ability of algorithms is often done incorrectly in the literature.

We introduce greedy policy search (GPS), a simple but high-performing method for learning a policy of test-time augmentation.

The deep weight prior is the generative model for kernels of convolutional neural networks, that acts as a prior distribution while training on new datasets.

It is possible to learn a zero-centered Gaussian distribution over the weights of a neural network by learning only variances, and it works surprisingly well.

We employ semi-conditional normalizing flow architecture that allows efficiently trains normalizing flows when only few labeled data points are available.

Domain adaptation via learning shared dynamics in a latent space with adversarial matching of latent states.

Inference-time stochastic batch normalization improves the performance of uncertainty estimation of ensembles.

The model allows to sparsify a DNN with an arbitrary pattern of spasticity e.g., neurons or convolutional filters.