# Semantically Decomposing the Latent Spaces of Generative Adversarial Networks

arXiv: https://arxiv.org/abs/1705.07904 · HTML: https://mlsanity.com/paper/1705.07904/

## Key facts

- Cited by 19 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 22 May 2017.

## Built on by (most cited first, 19 of 19)

- [Exposing flaws of generative model evaluation metrics and their unfair treatment of diffusion models](https://mlsanity.com/paper/2306.04675/) (2023)
- [Progressive Disentangled Representation Learning for Fine-Grained Controllable Talking Head Synthesis](https://mlsanity.com/paper/2211.14506/) (2022)
- [GAN-Control: Explicitly Controllable GANs](https://mlsanity.com/paper/2101.02477/) (2021)
- [IDiff-Face: Synthetic-based Face Recognition through Fizzy Identity-Conditioned Diffusion Models](https://mlsanity.com/paper/2308.04995/) (2023)
- [Diagonal Attention and Style-based GAN for Content-Style Disentanglement in Image Generation and Translation](https://mlsanity.com/paper/2103.16146/) (2021)
- [Orthogonal Jacobian Regularization for Unsupervised Disentanglement in Image Generation](https://mlsanity.com/paper/2108.07668/) (2021)
- [On the use of automatically generated synthetic image datasets for benchmarking face recognition](https://mlsanity.com/paper/2106.04215/) (2021)
- [Improving Visual Quality of Image Synthesis by A Token-based Generator with Transformers](https://mlsanity.com/paper/2111.03481/) (2021)
- [LinkGAN: Linking GAN Latents to Pixels for Controllable Image Synthesis](https://mlsanity.com/paper/2301.04604/) (2023)
- [DeepBlur: A Simple and Effective Method for Natural Image Obfuscation](https://mlsanity.com/paper/2104.02655/) (2021)
- [IA-FaceS: A Bidirectional Method for Semantic Face Editing](https://mlsanity.com/paper/2203.13097/) (2022)
- [Camera-Conditioned Stable Feature Generation for Isolated Camera Supervised Person Re-IDentification](https://mlsanity.com/paper/2203.15210/) (2022)
- [Unsupervised Disentanglement of Linear-Encoded Facial Semantics](https://mlsanity.com/paper/2103.16605/) (2021)
- [Expressive Talking Head Video Encoding in StyleGAN2 Latent-Space](https://mlsanity.com/paper/2203.14512/) (2022)
- [Training Invertible Neural Networks as Autoencoders](https://mlsanity.com/paper/2303.11239/) (2023)
- [Training face verification models from generated face identity data](https://mlsanity.com/paper/2108.00800/) (2021)
- [Video2StyleGAN: Encoding Video in Latent Space for Manipulation](https://mlsanity.com/paper/2206.13078/) (2022)
- [Deep denoising autoencoder-based non-invasive blood flow detection for arteriovenous fistula](https://mlsanity.com/paper/2306.06865/) (2023)
- [ADROIT: A Self-Supervised Framework for Learning Robust Representations for Active Learning](https://mlsanity.com/paper/2503.07506/) (2025)

## Abstract (arXiv)

We propose a new algorithm for training generative adversarial networks that jointly learns latent codes for both identities (e.g. individual humans) and observations (e.g. specific photographs). By fixing the identity portion of the latent codes, we can generate diverse images of the same subject, and by fixing the observation portion, we can traverse the manifold of subjects while maintaining contingent aspects such as lighting and pose. Our algorithm features a pairwise training scheme in which each sample from the generator consists of two images with a common identity code. Corresponding samples from the real dataset consist of two distinct photographs of the same subject. In order to fool the discriminator, the generator must produce pairs that are photorealistic, distinct, and appear to depict the same individual. We augment both the DCGAN and BEGAN approaches with Siamese discriminators to facilitate pairwise training. Experiments with human judges and an off-the-shelf face verification system demonstrate our algorithm's ability to generate convincing, identity-matched photographs.