# Disentangled Face Attribute Editing via Instance-Aware Latent Space Search

arXiv: https://arxiv.org/abs/2105.12660 · HTML: https://mlsanity.com/paper/2105.12660/

## Key facts

- Cited by 12 papers in the map (data through 14 Oct 2026).
- Builds on 28 of its 34 references that are in the map.
- First posted on arXiv 26 May 2021.

## Builds on (most cited first, 28 of 28)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [A Style-Based Generator Architecture for Generative Adversarial Networks](https://mlsanity.com/paper/1812.04948/) (2018)
- [Deep Learning Face Attributes in the Wild](https://mlsanity.com/paper/1411.7766/) (2014)
- [Analyzing and Improving the Image Quality of StyleGAN](https://mlsanity.com/paper/1912.04958/) (2019)
- [Progressive Growing of GANs for Improved Quality, Stability, and Variation](https://mlsanity.com/paper/1710.10196/) (2017)
- [Conditional Generative Adversarial Nets](https://mlsanity.com/paper/1411.1784/) (2014)
- [StarGAN: Unified Generative Adversarial Networks for Multi-Domain Image-to-Image Translation](https://mlsanity.com/paper/1711.09020/) (2017)
- [Interpreting the Latent Space of GANs for Semantic Face Editing](https://mlsanity.com/paper/1907.10786/) (2019)
- [Image2StyleGAN: How to Embed Images Into the StyleGAN Latent Space?](https://mlsanity.com/paper/1904.03189/) (2019)
- [GANSpace: Discovering Interpretable GAN Controls](https://mlsanity.com/paper/2004.02546/) (2020)
- [Conditional Image Synthesis With Auxiliary Classifier GANs](https://mlsanity.com/paper/1610.09585/) (2016)
- [In-Domain GAN Inversion for Real Image Editing](https://mlsanity.com/paper/2004.00049/) (2020)
- [Closed-Form Factorization of Latent Semantics in GANs](https://mlsanity.com/paper/2007.06600/) (2020)
- [Image2StyleGAN++: How to Edit the Embedded Images?](https://mlsanity.com/paper/1911.11544/) (2019)
- [Unsupervised Discovery of Interpretable Directions in the GAN Latent Space](https://mlsanity.com/paper/2002.03754/) (2020)
- [StyleRig: Rigging StyleGAN for 3D Control over Portrait Images](https://mlsanity.com/paper/2004.00121/) (2020)
- [AttGAN: Facial Attribute Editing by Only Changing What You Want](https://mlsanity.com/paper/1711.10678/) (2017)
- [Disentangled and Controllable Face Image Generation via 3D Imitative-Contrastive Learning](https://mlsanity.com/paper/2004.11660/) (2020)
- [GANalyze: Toward Visual Definitions of Cognitive Image Properties](https://mlsanity.com/paper/1906.10112/) (2019)
- [Stability](https://mlsanity.com/paper/1310.0150/) (2013)
- [STGAN: A Unified Selective Transfer Network for Arbitrary Image Attribute Editing](https://mlsanity.com/paper/1904.09709/) (2019)
- [Controlling generative models with continuous factors of variations](https://mlsanity.com/paper/2001.10238/) (2020)
- [Mask-Guided Portrait Editing with Conditional GANs](https://mlsanity.com/paper/1905.10346/) (2019)
- [CONFIG: Controllable Neural Face Image Generation](https://mlsanity.com/paper/2005.02671/) (2020)
- [RelGAN: Multi-Domain Image-to-Image Translation via Relative Attributes](https://mlsanity.com/paper/1908.07269/) (2019)
- [Learning Residual Images for Face Attribute Manipulation](https://mlsanity.com/paper/1612.05363/) (2016)
- [Exploring Unlabeled Faces for Novel Attribute Discovery](https://mlsanity.com/paper/1912.03085/) (2019)
- [Learning Disentangled Representations via Independent Subspaces](https://mlsanity.com/paper/1908.08989/) (2019)

## Built on by (most cited first, 12 of 12)

- [GAN-based Facial Attribute Manipulation](https://mlsanity.com/paper/2210.12683/) (2022)
- [Generative Adversarial Networks Unlearning](https://mlsanity.com/paper/2308.09881/) (2023)
- [AniFaceDrawing: Anime Portrait Exploration during Your Sketching](https://mlsanity.com/paper/2306.07476/) (2023)
- [A comprehensive survey on semantic facial attribute editing using generative adversarial networks](https://mlsanity.com/paper/2205.10587/) (2022)
- [SD-GAN: Semantic Decomposition for Face Image Synthesis with Discrete Attribute](https://mlsanity.com/paper/2207.05300/) (2022)
- [A Plug-and-Play Defensive Perturbation for Copyright Protection of DNN-based Applications](https://mlsanity.com/paper/2304.10679/) (2023)
- [Expanding the Latent Space of StyleGAN for Real Face Editing](https://mlsanity.com/paper/2204.12530/) (2022)
- [Identity-preserving Editing of Multiple Facial Attributes by Learning Global Edit Directions and Local Adjustments](https://mlsanity.com/paper/2309.14267/) (2023)
- [Self-supervised Enhancement of Latent Discovery in GANs](https://mlsanity.com/paper/2112.08835/) (2021)
- [RoNet: Rotation-oriented Continuous Image Translation](https://mlsanity.com/paper/2404.04474/) (2024)
- [HAIFAI: Human-AI Interaction for Mental Face Reconstruction](https://mlsanity.com/paper/2412.06323/) (2024)
- [U-Face: An Efficient and Generalizable Framework for Unsupervised Facial Attribute Editing via Subspace Learning](https://mlsanity.com/paper/2603.14004/) (2026)

## Abstract (arXiv)

Recent works have shown that a rich set of semantic directions exist in the latent space of Generative Adversarial Networks (GANs), which enables various facial attribute editing applications. However, existing methods may suffer poor attribute variation disentanglement, leading to unwanted change of other attributes when altering the desired one. The semantic directions used by existing methods are at attribute level, which are difficult to model complex attribute correlations, especially in the presence of attribute distribution bias in GAN's training set. In this paper, we propose a novel framework (IALS) that performs Instance-Aware Latent-Space Search to find semantic directions for disentangled attribute editing. The instance information is injected by leveraging the supervision from a set of attribute classifiers evaluated on the input images. We further propose a Disentanglement-Transformation (DT) metric to quantify the attribute transformation and disentanglement efficacy and find the optimal control factor between attribute-level and instance-specific directions based on it. Experimental results on both GAN-generated and real-world images collectively show that our method outperforms state-of-the-art methods proposed recently by a wide margin. Code is available at https://github.com/yxuhan/IALS.