# EqGAN: Feature Equalization Fusion for Few-shot Image Generation

arXiv: https://arxiv.org/abs/2307.14638 · HTML: https://mlsanity.com/paper/2307.14638/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 43 of its 52 references that are in the map.
- First posted on arXiv 27 Jul 2023.

## Builds on (most cited first, 30 of 43)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [U-Net: Convolutional Networks for Biomedical Image Segmentation](https://mlsanity.com/paper/1505.04597/) (2015)
- [The Unreasonable Effectiveness of Deep Features as a Perceptual Metric](https://mlsanity.com/paper/1801.03924/) (2018)
- [A Style-Based Generator Architecture for Generative Adversarial Networks](https://mlsanity.com/paper/1812.04948/) (2018)
- [Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks](https://mlsanity.com/paper/1703.03400/) (2017)
- [Prototypical Networks for Few-shot Learning](https://mlsanity.com/paper/1703.05175/) (2017)
- [Large Scale GAN Training for High Fidelity Natural Image Synthesis](https://mlsanity.com/paper/1809.11096/) (2018)
- [Matching Networks for One Shot Learning](https://mlsanity.com/paper/1606.04080/) (2016)
- [On First-Order Meta-Learning Algorithms](https://mlsanity.com/paper/1803.02999/) (2018)
- [Meta-Learning in Neural Networks: A Survey](https://mlsanity.com/paper/2004.05439/) (2020)
- [VGGFace2: A dataset for recognising faces across pose and age](https://mlsanity.com/paper/1710.08092/) (2017)
- [Encoding in Style: a StyleGAN Encoder for Image-to-Image Translation](https://mlsanity.com/paper/2008.00951/) (2020)
- [Conditional Image Synthesis With Auxiliary Classifier GANs](https://mlsanity.com/paper/1610.09585/) (2016)
- [Generalizing from a Few Examples: A Survey on Few-Shot Learning](https://mlsanity.com/paper/1904.05046/) (2019)
- [PANet: Few-Shot Image Semantic Segmentation with Prototype Alignment](https://mlsanity.com/paper/1908.06391/) (2019)
- [Tutorial on Variational Autoencoders](https://mlsanity.com/paper/1606.05908/) (2016)
- [Differentiable Augmentation for Data-Efficient GAN Training](https://mlsanity.com/paper/2006.10738/) (2020)
- [Data Augmentation Generative Adversarial Networks](https://mlsanity.com/paper/1711.04340/) (2017)
- [Few-shot Object Detection via Feature Reweighting](https://mlsanity.com/paper/1812.01866/) (2018)
- [Few-Shot Unsupervised Image-to-Image Translation](https://mlsanity.com/paper/1905.01723/) (2019)
- [A Comprehensive Survey of Few-shot Learning: Evolution, Applications, Challenges, and Opportunities](https://mlsanity.com/paper/2205.06743/) (2022)
- [Towards Faster and Stabilized GAN Training for High-fidelity Few-shot Image Synthesis](https://mlsanity.com/paper/2101.04775/) (2021)
- [DoveNet: Deep Image Harmonization via Domain Verification](https://mlsanity.com/paper/1911.13239/) (2019)
- [Multi-Scale Positive Sample Refinement for Few-Shot Object Detection](https://mlsanity.com/paper/2007.09384/) (2020)
- [Regularizing Generative Adversarial Networks under Limited Data](https://mlsanity.com/paper/2104.03310/) (2021)
- [Rethinking Image Inpainting via a Mutual Encoder-Decoder with Feature Equalizations](https://mlsanity.com/paper/2007.06929/) (2020)
- [Image Inpainting via Conditional Texture and Structure Dual Generation](https://mlsanity.com/paper/2108.09760/) (2021)
- [Making Images Real Again: A Comprehensive Survey on Deep Image Composition](https://mlsanity.com/paper/2106.14490/) (2021)
- [Recurrent Mask Refinement for Few-Shot Medical Image Segmentation](https://mlsanity.com/paper/2108.00622/) (2021)

## Abstract (arXiv)

Due to the absence of fine structure and texture information, existing fusion-based few-shot image generation methods suffer from unsatisfactory generation quality and diversity. To address this problem, we propose a novel feature Equalization fusion Generative Adversarial Network (EqGAN) for few-shot image generation. Unlike existing fusion strategies that rely on either deep features or local representations, we design two separate branches to fuse structures and textures by disentangling encoded features into shallow and deep contents. To refine image contents at all feature levels, we equalize the fused structure and texture semantics at different scales and supplement the decoder with richer information by skip connections. Since the fused structures and textures may be inconsistent with each other, we devise a consistent equalization loss between the equalized features and the intermediate output of the decoder to further align the semantics. Comprehensive experiments on three public datasets demonstrate that, EqGAN not only significantly improves generation performance with FID score (by up to 32.7%) and LPIPS score (by up to 4.19%), but also outperforms the state-of-the-arts in terms of accuracy (by up to 1.97%) for downstream classification tasks.