# MintNet: Building Invertible Neural Networks with Masked Convolutions

arXiv: https://arxiv.org/abs/1907.07945 · HTML: https://mlsanity.com/paper/1907.07945/

## Key facts

- Cited by 35 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 18 Jul 2019.

## Built on by (most cited first, 30 of 35)

- [Argmax Flows and Multinomial Diffusion: Learning Categorical Distributions](https://mlsanity.com/paper/2102.05379/) (2021)
- [Deep Generative Modelling: A Comparative Review of VAEs, GANs, Normalizing Flows, Energy-Based and Autoregressive Models](https://mlsanity.com/paper/2103.04922/) (2021)
- [Concrete Score Matching: Generalized Score Matching for Discrete Data](https://mlsanity.com/paper/2211.00802/) (2022)
- [Towards Blind Watermarking: Combining Invertible and Non-invertible Mechanisms](https://mlsanity.com/paper/2212.12678/) (2022)
- [Plug & Play Attacks: Towards Robust and Flexible Model Inversion Attacks](https://mlsanity.com/paper/2201.12179/) (2022)
- [Featurized Density Ratio Estimation](https://mlsanity.com/paper/2107.02212/) (2021)
- [Reversible Vision Transformers](https://mlsanity.com/paper/2302.04869/) (2023)
- [Implicit Normalizing Flows](https://mlsanity.com/paper/2103.09527/) (2021)
- [Re^2TAL: Rewiring Pretrained Video Backbones for Reversible Temporal Action Localization](https://mlsanity.com/paper/2211.14053/) (2022)
- [SAN: Inducing Metrizability of GAN with Discriminative Normalized Linear Layer](https://mlsanity.com/paper/2301.12811/) (2023)
- [Invertible Diffusion Models for Compressed Sensing](https://mlsanity.com/paper/2403.17006/) (2024)
- [Improved Input Reprogramming for GAN Conditioning](https://mlsanity.com/paper/2201.02692/) (2022)
- [A Compact Neural Network-based Algorithm for Robust Image Watermarking](https://mlsanity.com/paper/2112.13491/) (2021)
- [Training Energy-Based Normalizing Flow with Score-Matching Objectives](https://mlsanity.com/paper/2305.15267/) (2023)
- [Memory-Efficient Reversible Spiking Neural Networks](https://mlsanity.com/paper/2312.07922/) (2023)
- [PRIS: Practical robust invertible network for image steganography](https://mlsanity.com/paper/2309.13620/) (2023)
- [SoK: Data Reconstruction Attacks Against Machine Learning Models: Definition, Metrics, and Benchmark](https://mlsanity.com/paper/2506.07888/) (2025)
- [Multi-Resolution Continuous Normalizing Flows](https://mlsanity.com/paper/2106.08462/) (2021)
- [On Surjectivity of Neural Networks: Can you elicit any behavior from your model?](https://mlsanity.com/paper/2508.19445/) (2025)
- [A Unifying Framework for Parallelizing Sequential Models with Linear Dynamical Systems](https://mlsanity.com/paper/2509.21716/) (2025)
- [Certified Invertibility in Neural Networks via Mixed-Integer Programming](https://mlsanity.com/paper/2301.11783/) (2023)
- [The U-Net based GLOW for Optical-Flow-free Video Interframe Generation](https://mlsanity.com/paper/2103.09576/) (2021)
- [Coded-InvNet for Resilient Prediction Serving Systems](https://mlsanity.com/paper/2106.06445/) (2021)
- [Graphical Residual Flows](https://mlsanity.com/paper/2204.11846/) (2022)
- [FInC Flow: Fast and Invertible k × k Convolutions for Normalizing Flows](https://mlsanity.com/paper/2301.09266/) (2023)
- [Classification Diffusion Models: Revitalizing Density Ratio Estimation](https://mlsanity.com/paper/2402.10095/) (2024)
- [Generative Modeling: A Review](https://mlsanity.com/paper/2501.05458/) (2024)
- [Accelerate TarFlow Sampling with GS-Jacobi Iteration](https://mlsanity.com/paper/2505.12849/) (2025)
- [Learning Energy-Based Models from Stochastic Interpolants using Spatiotemporal Differences](https://mlsanity.com/paper/2605.26850/) (2026)
- [PaReprop: Fast Parallelized Reversible Backpropagation](https://mlsanity.com/paper/2306.09342/) (2023)

## Abstract (arXiv)

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 competitive likelihoods on MNIST, CIFAR-10 and ImageNet 32x32, with bits per dimension of 0.98, 3.32 and 4.06 respectively.