# Integrating Categorical Semantics into Unsupervised Domain Translation

arXiv: https://arxiv.org/abs/2010.01262 · HTML: https://mlsanity.com/paper/2010.01262/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 3 Oct 2020.

## Built on by (most cited first, 4 of 4)

- [So Different Yet So Alike! Constrained Unsupervised Text Style Transfer](https://mlsanity.com/paper/2205.04093/) (2022)
- [Semantics-aware Multi-modal Domain Translation:From LiDAR Point Clouds to Panoramic Color Images](https://mlsanity.com/paper/2106.13974/) (2021)
- [Compositional Discrete Latent Code for High Fidelity, Productive Diffusion Models](https://mlsanity.com/paper/2507.12318/) (2025)
- [Depth- and Semantics-aware Multi-modal Domain Translation: Generating 3D Panoramic Color Images from LiDAR Point Clouds](https://mlsanity.com/paper/2302.07661/) (2023)

## Abstract (arXiv)

While unsupervised domain translation (UDT) has seen a lot of success recently, we argue that mediating its translation via categorical semantic features could broaden its applicability. In particular, we demonstrate that categorical semantics improves the translation between perceptually different domains sharing multiple object categories. We propose a method to learn, in an unsupervised manner, categorical semantic features (such as object labels) that are invariant of the source and target domains. We show that conditioning the style encoder of unsupervised domain translation methods on the learned categorical semantics leads to a translation preserving the digits on MNISTleftrightarrowSVHN and to a more realistic stylization on Sketches→Reals.