# Domain Adaptation for Learning Generator from Paired Few-Shot Data

arXiv: https://arxiv.org/abs/2102.12765 · HTML: https://mlsanity.com/paper/2102.12765/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 13 of its 20 references that are in the map.
- First posted on arXiv 25 Feb 2021.

## Builds on (most cited first, 13 of 13)

- [Image-to-Image Translation with Conditional Adversarial Networks](https://mlsanity.com/paper/1611.07004/) (2016)
- [Auto-Encoding Variational Bayes](https://mlsanity.com/paper/1312.6114/) (2013)
- [Perceptual Losses for Real-Time Style Transfer and Super-Resolution](https://mlsanity.com/paper/1603.08155/) (2016)
- [Matching Networks for One Shot Learning](https://mlsanity.com/paper/1606.04080/) (2016)
- [Arbitrary Style Transfer in Real-time with Adaptive Instance Normalization](https://mlsanity.com/paper/1703.06868/) (2017)
- [Demystifying MMD GANs](https://mlsanity.com/paper/1801.01401/) (2018)
- [Learning to Compare: Relation Network for Few-Shot Learning](https://mlsanity.com/paper/1711.06025/) (2017)
- [Autoencoding beyond pixels using a learned similarity metric](https://mlsanity.com/paper/1512.09300/) (2015)
- [Coupled Generative Adversarial Networks](https://mlsanity.com/paper/1606.07536/) (2016)
- [f-VAEGAN-D2: A Feature Generating Framework for Any-Shot Learning](https://mlsanity.com/paper/1903.10132/) (2019)
- [Few-Shot Adversarial Domain Adaptation](https://mlsanity.com/paper/1711.02536/) (2017)
- [Semantic Jitter: Dense Supervision for Visual Comparisons via Synthetic Images](https://mlsanity.com/paper/1612.06341/) (2016)
- [Weakly Supervised Open-set Domain Adaptation by Dual-domain Collaboration](https://mlsanity.com/paper/1904.13179/) (2019)

## Abstract (arXiv)

We propose a Paired Few-shot GAN (PFS-GAN) model for learning generators with sufficient source data and a few target data. While generative model learning typically needs large-scale training data, our PFS-GAN not only uses the concept of few-shot learning but also domain shift to transfer the knowledge across domains, which alleviates the issue of obtaining low-quality generator when only trained with target domain data. The cross-domain datasets are assumed to have two properties: (1) each target-domain sample has its source-domain correspondence and (2) two domains share similar content information but different appearance. Our PFS-GAN aims to learn the disentangled representation from images, which composed of domain-invariant content features and domain-specific appearance features. Furthermore, a relation loss is introduced on the content features while shifting the appearance features to increase the structural diversity. Extensive experiments show that our method has better quantitative and qualitative results on the generated target-domain data with higher diversity in comparison to several baselines.