# Semantically Robust Unpaired Image Translation for Data with Unmatched Semantics Statistics

arXiv: https://arxiv.org/abs/2012.04932 · HTML: https://mlsanity.com/paper/2012.04932/

## Key facts

- Cited by 15 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 9 Dec 2020.

## Built on by (most cited first, 15 of 15)

- [StegoGAN: Leveraging Steganography for Non-Bijective Image-to-Image Translation](https://mlsanity.com/paper/2403.20142/) (2024)
- [Reward Fine-Tuning Two-Step Diffusion Models via Learning Differentiable Latent-Space Surrogate Reward](https://mlsanity.com/paper/2411.15247/) (2024)
- [Unpaired Image Translation via Vector Symbolic Architectures](https://mlsanity.com/paper/2209.02686/) (2022)
- [Exploring Semantic Consistency in Unpaired Image Translation to Generate Data for Surgical Applications](https://mlsanity.com/paper/2309.03048/) (2023)
- [ManiFest: Manifold Deformation for Few-shot Image Translation](https://mlsanity.com/paper/2111.13681/) (2021)
- [Exploring Negatives in Contrastive Learning for Unpaired Image-to-Image Translation](https://mlsanity.com/paper/2204.11018/) (2022)
- [Towards Pragmatic Semantic Image Synthesis for Urban Scenes](https://mlsanity.com/paper/2305.09726/) (2023)
- [Unsupervised Variational Translator for Bridging Image Restoration and High-Level Vision Tasks](https://mlsanity.com/paper/2408.08149/) (2024)
- [Unsupervised Synthetic Image Refinement via Contrastive Learning and Consistent Semantic-Structural Constraints](https://mlsanity.com/paper/2304.12591/) (2023)
- [Hierarchy Flow For High-Fidelity Image-to-Image Translation](https://mlsanity.com/paper/2308.06909/) (2023)
- [Masked Discriminators for Content-Consistent Unpaired Image-to-Image Translation](https://mlsanity.com/paper/2309.13188/) (2023)
- [I2AM: Interpreting Image-to-Image Latent Diffusion Models via Bi-Attribution Maps](https://mlsanity.com/paper/2407.12331/) (2024)
- [HyPER-GAN: Hybrid Patch-Based Image-to-Image Translation for Real-Time Photorealism Enhancement in Game Engines](https://mlsanity.com/paper/2603.10604/) (2026)
- [SemST: Semantically Consistent Multi-Scale Image Translation via Structure-Texture Alignment](https://mlsanity.com/paper/2310.04995/) (2023)
- [Image Translation with Kernel Prediction Networks for Semantic Segmentation](https://mlsanity.com/paper/2507.08554/) (2025)

## Abstract (arXiv)

Many applications of unpaired image-to-image translation require the input contents to be preserved semantically during translations. Unaware of the inherently unmatched semantics distributions between source and target domains, existing distribution matching methods (i.e., GAN-based) can give undesired solutions. In particular, although producing visually reasonable outputs, the learned models usually flip the semantics of the inputs. To tackle this without using extra supervision, we propose to enforce the translated outputs to be semantically invariant w.r.t. small perceptual variations of the inputs, a property we call "semantic robustness". By optimizing a robustness loss w.r.t. multi-scale feature space perturbations of the inputs, our method effectively reduces semantics flipping and produces translations that outperform existing methods both quantitatively and qualitatively.