# Invertible Autoencoder for domain adaptation

arXiv: https://arxiv.org/abs/1802.06869 · HTML: https://mlsanity.com/paper/1802.06869/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 10 Feb 2018.

## Built on by (most cited first, 10 of 10)

- [Benchmarking Invertible Architectures on Inverse Problems](https://mlsanity.com/paper/2101.10763/) (2021)
- [Mutual Information Estimation via Normalizing Flows](https://mlsanity.com/paper/2403.02187/) (2024)
- [Lifting Architectural Constraints of Injective Flows](https://mlsanity.com/paper/2306.01843/) (2023)
- [Watermarking Autoregressive Image Generation](https://mlsanity.com/paper/2506.16349/) (2025)
- [Training Invertible Neural Networks as Autoencoders](https://mlsanity.com/paper/2303.11239/) (2023)
- [Deep Symmetric Autoencoders from the Eckart-Young-Schmidt Perspective](https://mlsanity.com/paper/2506.11641/) (2025)
- [Harnessing AI for Inverse Partial Differential Equation Problems: Past, Present, and Prospects](https://mlsanity.com/paper/2605.16966/) (2026)
- [Generalized Neural Operator for Parametric and Boundary-Value Problems](https://mlsanity.com/paper/2607.21932/) (2026)
- [Deep Invertible Autoencoders for Dimensionality Reduction of Dynamical Systems](https://mlsanity.com/paper/2603.13496/) (2026)
- [Hybrid Lagrangian-Eulerian Model for Lagrangian Fluid Simulation](https://mlsanity.com/paper/2608.01164/) (2026)

## Abstract (arXiv)

The unsupervised image-to-image translation aims at finding a mapping between the source (A) and target (B) image domains, where in many applications aligned image pairs are not available at training. This is an ill-posed learning problem since it requires inferring the joint probability distribution from marginals. Joint learning of coupled mappings FAB: A rightarrow B and FBA: B rightarrow A is commonly used by the state-of-the-art methods, like CycleGAN [Zhu et al., 2017], to learn this translation by introducing cycle consistency requirement to the learning problem, i.e. FAB(FBA(B)) ≈ B and FBA(FAB(A)) ≈ A. Cycle consistency enforces the preservation of the mutual information between input and translated images. However, it does not explicitly enforce FBA to be an inverse operation to FAB. We propose a new deep architecture that we call invertible autoencoder (InvAuto) to explicitly enforce this relation. This is done by forcing an encoder to be an inverted version of the decoder, where corresponding layers perform opposite mappings and share parameters. The mappings are constrained to be orthonormal. The resulting architecture leads to the reduction of the number of trainable parameters (up to 2 times). We present image translation results on benchmark data sets and demonstrate state-of-the art performance of our approach. Finally, we test the proposed domain adaptation method on the task of road video conversion. We demonstrate that the videos converted with InvAuto have high quality and show that the NVIDIA neural-network-based end-to-end learning system for autonomous driving, known as PilotNet, trained on real road videos performs well when tested on the converted ones.