Papers › FInC Flow: Fast and Invertible k ×k Convolutions for Normalizing Flows

FInC Flow: Fast and Invertible k ×k Convolutions for Normalizing Flows

23 Jan 2023arXiv:2301.09266archive 2025-07-28

Aditya Kallappa, Sandeep Nagar, Girish Varma

Invertible convolutions have been an essential element for building expressive normalizing flow-based generative models since their introduction in Glow. Several attempts have been made to design invertible k ×k convolutions that are efficient in training and sampling passes. Though these attempts have improved the expressivity and sampling efficiency, they severely lagged behind Glow which used only 1 ×1 convolutions in terms of sampling time. Also, many of the approaches mask a large number of parameters of the underlying convolution, resulting in lower expressivity on a fixed run-time budget. We propose a k ×k convolutional layer and Deep Normalizing Flow architecture which i.) has a fast parallel inversion algorithm with running time O$(n k^2)$ (n is height and width of the input image and k is kernel size), ii.) masks the minimal amount of learnable parameters in a layer. iii.) gives better forward pass and sampling times comparable to other k ×k convolution-based models on real-world benchmarks. We provide an implementation of the proposed parallel algorithm for sampling using our invertible convolutions on GPUs. Benchmarks on CIFAR-10, ImageNet, and CelebA datasets show comparable performance to previous works regarding bits per dimension while significantly improving the sampling time.

PaperPDF

Code

No code repository is listed for this paper in the archive or in Syntology's graph.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Image Generation

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Image Generation CelebA FInCFlow bpd (8-bits) NaN #1 of 1 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Methods

Activation NormalizationAffine CouplingGLOWInvertible 1x1 ConvolutionNormalizing Flows

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections