# Few-Shot Generative Model Adaption via Identity Injection and Preservation

arXiv: https://arxiv.org/abs/2603.22965 · HTML: https://mlsanity.com/paper/2603.22965/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 27 of its 40 references that are in the map.
- First posted on arXiv 24 Mar 2026.

## Builds on (most cited first, 27 of 27)

- [The Unreasonable Effectiveness of Deep Features as a Perceptual Metric](https://mlsanity.com/paper/1801.03924/) (2018)
- [DINOv2: Learning Robust Visual Features without Supervision](https://mlsanity.com/paper/2304.07193/) (2023)
- [Hierarchical Text-Conditional Image Generation with CLIP Latents](https://mlsanity.com/paper/2204.06125/) (2022)
- [A Style-Based Generator Architecture for Generative Adversarial Networks](https://mlsanity.com/paper/1812.04948/) (2018)
- [Analyzing and Improving the Image Quality of StyleGAN](https://mlsanity.com/paper/1912.04958/) (2019)
- [Arbitrary Style Transfer in Real-time with Adaptive Instance Normalization](https://mlsanity.com/paper/1703.06868/) (2017)
- [LSUN: Construction of a Large-scale Image Dataset using Deep Learning with Humans in the Loop](https://mlsanity.com/paper/1506.03365/) (2015)
- [Training Generative Adversarial Networks with Limited Data](https://mlsanity.com/paper/2006.06676/) (2020)
- [StarGAN v2: Diverse Image Synthesis for Multiple Domains](https://mlsanity.com/paper/1912.01865/) (2019)
- [Deeper, Broader and Artier Domain Generalization](https://mlsanity.com/paper/1710.03077/) (2017)
- [Few-shot Image Generation via Cross-domain Correspondence](https://mlsanity.com/paper/2104.06820/) (2021)
- [Style Injection in Diffusion: A Training-free Approach for Adapting Large-scale Diffusion Models for Style Transfer](https://mlsanity.com/paper/2312.09008/) (2023)
- [Semantic Image Inpainting with Deep Generative Models](https://mlsanity.com/paper/1607.07539/) (2016)
- [Transferring GANs: generating images from limited data](https://mlsanity.com/paper/1805.01677/) (2018)
- [Efficient Domain Generalization via Common-Specific Low-Rank Decomposition](https://mlsanity.com/paper/2003.12815/) (2020)
- [Freeze the Discriminator: a Simple Baseline for Fine-Tuning GANs](https://mlsanity.com/paper/2002.10964/) (2020)
- [Learning to Balance Specificity and Invariance for In and Out of Domain Generalization](https://mlsanity.com/paper/2008.12839/) (2020)
- [Few-shot Image Generation with Elastic Weight Consolidation](https://mlsanity.com/paper/2012.02780/) (2020)
- [MineGAN: effective knowledge transfer from GANs to target domains with few images](https://mlsanity.com/paper/1912.05270/) (2019)
- [Image Generation From Small Datasets via Batch Statistics Adaptation](https://mlsanity.com/paper/1904.01774/) (2019)
- [Few Shot Generative Model Adaption via Relaxed Spatial Structural Alignment](https://mlsanity.com/paper/2203.04121/) (2022)
- [A Closer Look at Few-shot Image Generation](https://mlsanity.com/paper/2205.03805/) (2022)
- [One-Shot Generative Domain Adaptation](https://mlsanity.com/paper/2111.09876/) (2021)
- [Exploring Incompatible Knowledge Transfer in Few-shot Image Generation](https://mlsanity.com/paper/2304.07574/) (2023)
- [DynaGAN: Dynamic Few-shot Adaptation of GANs to Multiple Domains](https://mlsanity.com/paper/2211.14554/) (2022)
- [Eliminating Contextual Prior Bias for Semantic Image Editing via Dual-Cycle Diffusion](https://mlsanity.com/paper/2302.02394/) (2023)
- [Few-shot Image Generation via Style Adaptation and Content Preservation](https://mlsanity.com/paper/2311.18169/) (2023)

## Abstract (arXiv)

Training generative models with limited data presents severe challenges of mode collapse. A common approach is to adapt a large pretrained generative model upon a target domain with very few samples (fewer than 10), known as few-shot generative model adaptation. However, existing methods often suffer from forgetting source domain identity knowledge during adaptation, which degrades the quality of generated images in the target domain. To address this, we propose Identity Injection and Preservation (I2P), which leverages identity injection and consistency alignment to preserve the source identity knowledge. Specifically, we first introduce an identity injection module that integrates source domain identity knowledge into the target domain's latent space, ensuring the generated images retain key identity knowledge of the source domain. Second, we design an identity substitution module, which includes a style-content decoupler and a reconstruction modulator, to further enhance source domain identity preservation. We enforce identity consistency constraints by aligning features from identity substitution, thereby preserving identity knowledge. Both quantitative and qualitative experiments show that our method achieves substantial improvements over state-of-the-art methods on multiple public datasets and 5 metrics.