MintNet: Building Invertible Neural Networks with Masked Convolutions

07/18/2019
by   Yang Song, et al.
3

We propose a new way of constructing invertible neural networks by combining simple building blocks with a novel set of composition rules. This leads to a rich set of invertible architectures, including those similar to ResNets. Inversion is achieved with a locally convergent iterative procedure that is parallelizable and very fast in practice. Additionally, the determinant of the Jacobian can be computed analytically and efficiently, enabling their generative use as flow models. To demonstrate their flexibility, we show that our invertible neural networks are competitive with ResNets on MNIST and CIFAR-10 classification. When trained as generative models, our invertible networks achieve new state-of-the-art likelihoods on MNIST, CIFAR-10 and ImageNet 32x32, with bits per dimension of 0.98, 3.32 and 4.06 respectively.

READ FULL TEXT

Please sign up or login with your details

Forgot password? Click here to reset