You Only Train Once: Loss-Conditional Training of Deep Networks

Alexey Dosovitskiy, Josip Djolonga

TL;DR: A method to train a single model simultaneously minimizing a family of loss functions instead of training a set of per-loss models.

Abstract: In many machine learning problems, loss functions are weighted sums of several terms. A typical approach to dealing with these is to train multiple separate models with different selections of weights and then either choose the best one according to some criterion or keep multiple models if it is desirable to maintain a diverse set of solutions. This is inefficient both at training and at inference time. We propose a method that allows replacing multiple models trained on one loss function each by a single model trained on a distribution of losses. At test time a model trained this way can be conditioned to generate outputs corresponding to any loss from the training distribution of losses. We demonstrate this approach on three tasks with parametrized losses: beta-VAE, learned image compression, and fast style transfer.

Keywords: deep learning, image generation

Data: [CIFAR-10](https://paperswithcode.com/dataset/cifar-10), [ImageNet](https://paperswithcode.com/dataset/imagenet)