# Semi-supervised Learning for Few-shot Image-to-Image Translation

arXiv: https://arxiv.org/abs/2003.13853 · HTML: https://mlsanity.com/paper/2003.13853/

## Key facts

- Cited by 25 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 30 Mar 2020.

## Built on by (most cited first, 25 of 25)

- [Few-shot Image Generation via Cross-domain Correspondence](https://mlsanity.com/paper/2104.06820/) (2021)
- [Image-to-Image Translation: Methods and Applications](https://mlsanity.com/paper/2101.08629/) (2021)
- [Few Shot Generative Model Adaption via Relaxed Spatial Structural Alignment](https://mlsanity.com/paper/2203.04121/) (2022)
- [Revisiting Consistency Regularization for Semi-supervised Change Detection in Remote Sensing Images](https://mlsanity.com/paper/2204.08454/) (2022)
- [Attribute Group Editing for Reliable Few-shot Image Generation](https://mlsanity.com/paper/2203.08422/) (2022)
- [Few-shot Image Generation via Masked Discrimination](https://mlsanity.com/paper/2210.15194/) (2022)
- [MaxMatch: Semi-Supervised Learning with Worst-Case Consistency](https://mlsanity.com/paper/2209.12611/) (2022)
- [Multi-level Metric Learning for Few-shot Image Recognition](https://mlsanity.com/paper/2103.11383/) (2021)
- [ManiFest: Manifold Deformation for Few-shot Image Translation](https://mlsanity.com/paper/2111.13681/) (2021)
- [Few-shot Image Generation Using Discrete Content Representation](https://mlsanity.com/paper/2207.10833/) (2022)
- [Stable Attribute Group Editing for Reliable Few-shot Image Generation](https://mlsanity.com/paper/2302.00179/) (2023)
- [Few-Shot Model Adaptation for Customized Facial Landmark Detection, Segmentation, Stylization and Shadow Removal](https://mlsanity.com/paper/2104.09457/) (2021)
- [LANIT: Language-Driven Image-to-Image Translation for Unlabeled Data](https://mlsanity.com/paper/2208.14889/) (2022)
- [Towards Identifiable Unsupervised Domain Translation: A Diversified Distribution Matching Approach](https://mlsanity.com/paper/2401.09671/) (2024)
- [Local Propagation for Few-Shot Learning](https://mlsanity.com/paper/2101.01480/) (2021)
- [Few-shot Semantic Image Synthesis Using StyleGAN Prior](https://mlsanity.com/paper/2103.14877/) (2021)
- [Attention in Diffusion Model: A Survey](https://mlsanity.com/paper/2504.03738/) (2025)
- [UGC: Unified GAN Compression for Efficient Image-to-Image Translation](https://mlsanity.com/paper/2309.09310/) (2023)
- [AesFA: An Aesthetic Feature-Aware Arbitrary Neural Style Transfer](https://mlsanity.com/paper/2312.05928/) (2023)
- [Deep Photo Scan: Semi-Supervised Learning for dealing with the real-world degradation in Smartphone Photo Scanning](https://mlsanity.com/paper/2102.06120/) (2021)
- [3D-Aware Multi-Class Image-to-Image Translation with NeRFs](https://mlsanity.com/paper/2303.15012/) (2023)
- [Minimally Supervised Learning using Topological Projections in Self-Organizing Maps](https://mlsanity.com/paper/2401.06923/) (2024)
- [Leveraging Local Domains for Image-to-Image Translation](https://mlsanity.com/paper/2109.04468/) (2021)
- [A Semi-Paired Approach For Label-to-Image Translation](https://mlsanity.com/paper/2306.13585/) (2023)
- [Few-shot Face Image Translation via GAN Prior Distillation](https://mlsanity.com/paper/2301.12257/) (2023)

## Abstract (arXiv)

In the last few years, unpaired image-to-image translation has witnessed remarkable progress. Although the latest methods are able to generate realistic images, they crucially rely on a large number of labeled images. Recently, some methods have tackled the challenging setting of few-shot image-to-image translation, reducing the labeled data requirements for the target domain during inference. In this work, we go one step further and reduce the amount of required labeled data also from the source domain during training. To do so, we propose applying semi-supervised learning via a noise-tolerant pseudo-labeling procedure. We also apply a cycle consistency constraint to further exploit the information from unlabeled images, either from the same dataset or external. Additionally, we propose several structural modifications to facilitate the image translation task under these circumstances. Our semi-supervised method for few-shot image translation, called SEMIT, achieves excellent results on four different datasets using as little as 10% of the source labels, and matches the performance of the main fully-supervised competitor using only 20% labeled data. Our code and models are made public at: https://github.com/yaxingwang/SEMIT.