# Generative Hierarchical Features from Synthesizing Images

arXiv: https://arxiv.org/abs/2007.10379 · HTML: https://mlsanity.com/paper/2007.10379/

## Key facts

- Cited by 83 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 20 Jul 2020.

## Built on by (most cited first, 30 of 83)

- [SDEdit: Guided Image Synthesis and Editing with Stochastic Differential Equations](https://mlsanity.com/paper/2108.01073/) (2021)
- [Label-Efficient Semantic Segmentation with Diffusion Models](https://mlsanity.com/paper/2112.03126/) (2021)
- [GAN Inversion: A Survey](https://mlsanity.com/paper/2101.05278/) (2021)
- [Synthetic Data from Diffusion Models Improves ImageNet Classification](https://mlsanity.com/paper/2304.08466/) (2023)
- [ReStyle: A Residual-Based StyleGAN Encoder via Iterative Refinement](https://mlsanity.com/paper/2104.02699/) (2021)
- [MAGE: MAsked Generative Encoder to Unify Representation Learning and Image Synthesis](https://mlsanity.com/paper/2211.09117/) (2022)
- [Encoder-based Domain Tuning for Fast Personalization of Text-to-Image Models](https://mlsanity.com/paper/2302.12228/) (2023)
- [High-Fidelity GAN Inversion for Image Attribute Editing](https://mlsanity.com/paper/2109.06590/) (2021)
- [StyleGAN-NADA: CLIP-Guided Domain Adaptation of Image Generators](https://mlsanity.com/paper/2108.00946/) (2021)
- [Explaining in Style: Training a GAN to explain a classifier in StyleSpace](https://mlsanity.com/paper/2104.13369/) (2021)
- [3D-aware Image Synthesis via Learning Structural and Textural Representations](https://mlsanity.com/paper/2112.10759/) (2021)
- [D2C: Diffusion-Denoising Models for Few-shot Conditional Generation](https://mlsanity.com/paper/2106.06819/) (2021)
- [DisCoScene: Spatially Disentangled Generative Radiance Fields for Controllable 3D-aware Scene Synthesis](https://mlsanity.com/paper/2212.11984/) (2022)
- [Data-Efficient Instance Generation from Instance Discrimination](https://mlsanity.com/paper/2106.04566/) (2021)
- [Labels4Free: Unsupervised Segmentation using StyleGAN](https://mlsanity.com/paper/2103.14968/) (2021)
- [Low-Rank Subspaces in GANs](https://mlsanity.com/paper/2106.04488/) (2021)
- [Region-Aware Face Swapping](https://mlsanity.com/paper/2203.04564/) (2022)
- [SceneComposer: Any-Level Semantic Image Synthesis](https://mlsanity.com/paper/2211.11742/) (2022)
- [One-Shot Generative Domain Adaptation](https://mlsanity.com/paper/2111.09876/) (2021)
- [Exploiting Diffusion Prior for Generalizable Dense Prediction](https://mlsanity.com/paper/2311.18832/) (2023)
- [DreamTeacher: Pretraining Image Backbones with Deep Generative Models](https://mlsanity.com/paper/2307.07487/) (2023)
- [State-of-the-Art in the Architecture, Methods and Applications of StyleGAN](https://mlsanity.com/paper/2202.14020/) (2022)
- [3DitScene: Editing Any Scene via Language-guided Disentangled Gaussian Splatting](https://mlsanity.com/paper/2405.18424/) (2024)
- [High-fidelity GAN Inversion with Padding Space](https://mlsanity.com/paper/2203.11105/) (2022)
- [Region-Based Semantic Factorization in GANs](https://mlsanity.com/paper/2202.09649/) (2022)
- [Improving GANs with A Dynamic Discriminator](https://mlsanity.com/paper/2209.09897/) (2022)
- [GLEAN: Generative Latent Bank for Image Super-Resolution and Beyond](https://mlsanity.com/paper/2207.14812/) (2022)
- [StyleInV: A Temporal Style Modulated Inversion Network for Unconditional Video Generation](https://mlsanity.com/paper/2308.16909/) (2023)
- [Hierarchical Diffusion Autoencoders and Disentangled Image Manipulation](https://mlsanity.com/paper/2304.11829/) (2023)
- [LibreFace: An Open-Source Toolkit for Deep Facial Expression Analysis](https://mlsanity.com/paper/2308.10713/) (2023)

## Abstract (arXiv)

Generative Adversarial Networks (GANs) have recently advanced image synthesis by learning the underlying distribution of the observed data. However, how the features learned from solving the task of image generation are applicable to other vision tasks remains seldom explored. In this work, we show that learning to synthesize images can bring remarkable hierarchical visual features that are generalizable across a wide range of applications. Specifically, we consider the pre-trained StyleGAN generator as a learned loss function and utilize its layer-wise representation to train a novel hierarchical encoder. The visual feature produced by our encoder, termed as Generative Hierarchical Feature (GH-Feat), has strong transferability to both generative and discriminative tasks, including image editing, image harmonization, image classification, face verification, landmark detection, and layout prediction. Extensive qualitative and quantitative experimental results demonstrate the appealing performance of GH-Feat.