Transflow Learning: Repurposing Flow Models Without Retraining
This method addresses the need for efficient model adaptation in machine learning, offering a training-free solution that is incremental in improving manipulation capabilities.
The paper tackles the problem of requiring extensive training for manipulating pre-trained generative models by introducing Transflow Learning, which repurposes these models without retraining using Bayesian inference to warp the latent probability distribution, enabling tasks like neural style transfer and few-shot classification.
It is well known that deep generative models have a rich latent space, and that it is possible to smoothly manipulate their outputs by traversing this latent space. Recently, architectures have emerged that allow for more complex manipulations, such as making an image look as though it were from a different class, or painted in a certain style. These methods typically require large amounts of training in order to learn a single class of manipulations. We present Transflow Learning, a method for transforming a pre-trained generative model so that its outputs more closely resemble data that we provide afterwards. In contrast to previous methods, Transflow Learning does not require any training at all, and instead warps the probability distribution from which we sample latent vectors using Bayesian inference. Transflow Learning can be used to solve a wide variety of tasks, such as neural style transfer and few-shot classification.