# Semi-Supervised StyleGAN for Disentanglement Learning

arXiv: https://arxiv.org/abs/2003.03461 · HTML: https://mlsanity.com/paper/2003.03461/

## Key facts

- Cited by 43 papers in the map (data through 7 Oct 2026).
- First posted on arXiv 6 Mar 2020.

## Built on by (most cited first, 30 of 43)

- [Unsupervised Learning of Compositional Energy Concepts](https://mlsanity.com/paper/2111.03042/) (2021)
- [Controllable and Compositional Generation with Latent-Space Energy-Based Models](https://mlsanity.com/paper/2110.10873/) (2021)
- [Not All Neuro-Symbolic Concepts Are Created Equal: Analysis and Mitigation of Reasoning Shortcuts](https://mlsanity.com/paper/2305.19951/) (2023)
- [Diffusion Models Beat GANs on Image Classification](https://mlsanity.com/paper/2307.08702/) (2023)
- [Learning Disentangled Representations in the Imaging Domain](https://mlsanity.com/paper/2108.12043/) (2021)
- [Disentanglement via Latent Quantization](https://mlsanity.com/paper/2305.18378/) (2023)
- [Counterfactual State Explanations for Reinforcement Learning Agents via Generative Deep Learning](https://mlsanity.com/paper/2101.12446/) (2021)
- [Meta-Learning Dynamics Forecasting Using Task Inference](https://mlsanity.com/paper/2102.10271/) (2021)
- [Predict, Prevent, and Evaluate: Disentangled Text-Driven Image Manipulation Empowered by Pre-Trained Vision-Language Model](https://mlsanity.com/paper/2111.13333/) (2021)
- [Do text-free diffusion models learn discriminative visual representations?](https://mlsanity.com/paper/2311.17921/) (2023)
- [An Image is Worth More Than a Thousand Words: Towards Disentanglement in the Wild](https://mlsanity.com/paper/2106.15610/) (2021)
- [FaceController: Controllable Attribute Editing for Face in the Wild](https://mlsanity.com/paper/2102.11464/) (2021)
- [On Causally Disentangled Representations](https://mlsanity.com/paper/2112.05746/) (2021)
- [Algorithm Fairness in AI for Medicine and Healthcare](https://mlsanity.com/paper/2110.00603/) (2021)
- [Disentangled Representations from Non-Disentangled Models](https://mlsanity.com/paper/2102.06204/) (2021)
- [Compositional Image Decomposition with Diffusion Models](https://mlsanity.com/paper/2406.19298/) (2024)
- [Latent Transformations via NeuralODEs for GAN-based Image Editing](https://mlsanity.com/paper/2111.14825/) (2021)
- [Flow Factorized Representation Learning](https://mlsanity.com/paper/2309.13167/) (2023)
- [medXGAN: Visual Explanations for Medical Classifiers through a Generative Latent Space](https://mlsanity.com/paper/2204.05376/) (2022)
- [Hadamard product in deep learning: Introduction, Advances and Challenges](https://mlsanity.com/paper/2504.13112/) (2025)
- [Cross-Modal Perceptionist: Can Face Geometry be Gleaned from Voices?](https://mlsanity.com/paper/2203.09824/) (2022)
- [Disentangling representations of retinal images with generative models](https://mlsanity.com/paper/2402.19186/) (2024)
- [Semi-Supervised Disentanglement of Class-Related and Class-Independent Factors in VAE](https://mlsanity.com/paper/2102.00892/) (2021)
- [DeepFN: Towards Generalizable Facial Action Unit Recognition with Deep Face Normalization](https://mlsanity.com/paper/2103.02484/) (2021)
- [CoralStyleCLIP: Co-optimized Region and Layer Selection for Image Editing](https://mlsanity.com/paper/2303.05031/) (2023)
- [FitGAN: Fit- and Shape-Realistic Generative Adversarial Networks for Fashion](https://mlsanity.com/paper/2206.11768/) (2022)
- [Statistical and structural identifiability in representation learning](https://mlsanity.com/paper/2603.11970/) (2026)
- [Synthesis in Style: Semantic Segmentation of Historical Documents using Synthetic Data](https://mlsanity.com/paper/2107.06777/) (2021)
- [Unsupervised Representation Learning from Sparse Transformation Analysis](https://mlsanity.com/paper/2410.05564/) (2024)
- [Symbolic Disentangled Representations for Images](https://mlsanity.com/paper/2412.19847/) (2024)

## Abstract (arXiv)

Disentanglement learning is crucial for obtaining disentangled representations and controllable generation. Current disentanglement methods face several inherent limitations: difficulty with high-resolution images, primarily focusing on learning disentangled representations, and non-identifiability due to the unsupervised setting. To alleviate these limitations, we design new architectures and loss functions based on StyleGAN (Karras et al., 2019), for semi-supervised high-resolution disentanglement learning. We create two complex high-resolution synthetic datasets for systematic testing. We investigate the impact of limited supervision and find that using only 0.25%~2.5% of labeled data is sufficient for good disentanglement on both synthetic and real datasets. We propose new metrics to quantify generator controllability, and observe there may exist a crucial trade-off between disentangled representation learning and controllable generation. We also consider semantic fine-grained image editing to achieve better generalization to unseen images.