# Stacked Generative Adversarial Networks

arXiv: https://arxiv.org/abs/1612.04357 · HTML: https://mlsanity.com/paper/1612.04357/

## Key facts

- Cited by 44 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 13 Dec 2016.

## Built on by (most cited first, 30 of 44)

- [Generative Adversarial Networks](https://mlsanity.com/paper/2203.00667/) (2022)
- [ReAct: Out-of-distribution Detection With Rectified Activations](https://mlsanity.com/paper/2111.12797/) (2021)
- [On the Importance of Gradients for Detecting Distributional Shifts in the Wild](https://mlsanity.com/paper/2110.00218/) (2021)
- [Deep Generative Modelling: A Comparative Review of VAEs, GANs, Normalizing Flows, Energy-Based and Autoregressive Models](https://mlsanity.com/paper/2103.04922/) (2021)
- [Projected GANs Converge Faster](https://mlsanity.com/paper/2111.01007/) (2021)
- [Exposing flaws of generative model evaluation metrics and their unfair treatment of diffusion models](https://mlsanity.com/paper/2306.04675/) (2023)
- [Towards Faster and Stabilized GAN Training for High-fidelity Few-shot Image Synthesis](https://mlsanity.com/paper/2101.04775/) (2021)
- [Can multi-label classification networks know what they don't know?](https://mlsanity.com/paper/2109.14162/) (2021)
- [IconShop: Text-Guided Vector Icon Synthesis with Autoregressive Transformers](https://mlsanity.com/paper/2304.14400/) (2023)
- [RankFeat: Rank-1 Feature Removal for Out-of-distribution Detection](https://mlsanity.com/paper/2209.08590/) (2022)
- [VTGAN: Semi-supervised Retinal Image Synthesis and Disease Prediction using Vision Transformers](https://mlsanity.com/paper/2104.06757/) (2021)
- [Linear Semantics in Generative Adversarial Networks](https://mlsanity.com/paper/2104.00487/) (2021)
- [MEGAN: Mixture of Experts of Generative Adversarial Networks for Multimodal Image Generation](https://mlsanity.com/paper/1805.02481/) (2018)
- [On the Fairness of Generative Adversarial Networks (GANs)](https://mlsanity.com/paper/2103.00950/) (2021)
- [SinIR: Efficient General Image Manipulation with Single Image Reconstruction](https://mlsanity.com/paper/2106.07140/) (2021)
- [Adversarial sampling of unknown and high-dimensional conditional distributions](https://mlsanity.com/paper/2111.05962/) (2021)
- [Optimal Linear Subspace Search: Learning to Construct Fast and High-Quality Schedulers for Diffusion Models](https://mlsanity.com/paper/2305.14677/) (2023)
- [PTNet: A High-Resolution Infant MRI Synthesizer Based on Transformer](https://mlsanity.com/paper/2105.13993/) (2021)
- [DiffSynth: Latent In-Iteration Deflickering for Realistic Video Synthesis](https://mlsanity.com/paper/2308.03463/) (2023)
- [Scale-wise Distillation of Diffusion Models](https://mlsanity.com/paper/2503.16397/) (2025)
- [CRD-CGAN: Category-Consistent and Relativistic Constraints for Diverse Text-to-Image Generation](https://mlsanity.com/paper/2107.13516/) (2021)
- [Model Extraction and Defenses on Generative Adversarial Networks](https://mlsanity.com/paper/2101.02069/) (2021)
- [NVS-MonoDepth: Improving Monocular Depth Prediction with Novel View Synthesis](https://mlsanity.com/paper/2112.12577/) (2021)
- [DO-GAN: A Double Oracle Framework for Generative Adversarial Networks](https://mlsanity.com/paper/2102.08577/) (2021)
- [Reconstruction-based Out-of-Distribution Detection for Short-Range FMCW Radar](https://mlsanity.com/paper/2302.14192/) (2023)
- [A Realism Metric for Generated LiDAR Point Clouds](https://mlsanity.com/paper/2208.14958/) (2022)
- [Extracting Semantic Knowledge from GANs with Unsupervised Learning](https://mlsanity.com/paper/2211.16710/) (2022)
- [DuelGAN: A Duel Between Two Discriminators Stabilizes the GAN Training](https://mlsanity.com/paper/2101.07524/) (2021)
- [Adversarial Stacked Auto-Encoders for Fair Representation Learning](https://mlsanity.com/paper/2107.12826/) (2021)
- [Quantifying point cloud realism through adversarially learned latent representations](https://mlsanity.com/paper/2109.11775/) (2021)

## Abstract (arXiv)

In this paper, we propose a novel generative model named Stacked Generative Adversarial Networks (SGAN), which is trained to invert the hierarchical representations of a bottom-up discriminative network. Our model consists of a top-down stack of GANs, each learned to generate lower-level representations conditioned on higher-level representations. A representation discriminator is introduced at each feature hierarchy to encourage the representation manifold of the generator to align with that of the bottom-up discriminative network, leveraging the powerful discriminative representations to guide the generative model. In addition, we introduce a conditional loss that encourages the use of conditional information from the layer above, and a novel entropy loss that maximizes a variational lower bound on the conditional entropy of generator outputs. We first train each stack independently, and then train the whole model end-to-end. Unlike the original GAN that uses a single noise vector to represent all the variations, our SGAN decomposes variations into multiple levels and gradually resolves uncertainties in the top-down generative process. Based on visual inspection, Inception scores and visual Turing test, we demonstrate that SGAN is able to generate images of much higher quality than GANs without stacking.