# Improving GAN Equilibrium by Raising Spatial Awareness

arXiv: https://arxiv.org/abs/2112.00718 · HTML: https://mlsanity.com/paper/2112.00718/

## Key facts

- Cited by 22 papers in the map (data through 14 Oct 2026).
- Builds on 31 of its 39 references that are in the map.
- First posted on arXiv 1 Dec 2021.

## Builds on (most cited first, 30 of 31)

- [Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localization](https://mlsanity.com/paper/1610.02391/) (2016)
- [A Style-Based Generator Architecture for Generative Adversarial Networks](https://mlsanity.com/paper/1812.04948/) (2018)
- [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)
- [Large Scale GAN Training for High Fidelity Natural Image Synthesis](https://mlsanity.com/paper/1809.11096/) (2018)
- [Learning Deep Features for Discriminative Localization](https://mlsanity.com/paper/1512.04150/) (2015)
- [Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks](https://mlsanity.com/paper/1511.06434/) (2015)
- [Arbitrary Style Transfer in Real-time with Adaptive Instance Normalization](https://mlsanity.com/paper/1703.06868/) (2017)
- [Spectral Normalization for Generative Adversarial Networks](https://mlsanity.com/paper/1802.05957/) (2018)
- [LSUN: Construction of a Large-scale Image Dataset using Deep Learning with Humans in the Loop](https://mlsanity.com/paper/1506.03365/) (2015)
- [Semantic Image Synthesis with Spatially-Adaptive Normalization](https://mlsanity.com/paper/1903.07291/) (2019)
- [Training Generative Adversarial Networks with Limited Data](https://mlsanity.com/paper/2006.06676/) (2020)
- [High-Resolution Image Synthesis and Semantic Manipulation with Conditional GANs](https://mlsanity.com/paper/1711.11585/) (2017)
- [Self-Attention Generative Adversarial Networks](https://mlsanity.com/paper/1805.08318/) (2018)
- [GIRAFFE: Representing Scenes as Compositional Generative Neural Feature Fields](https://mlsanity.com/paper/2011.12100/) (2020)
- [Interpreting the Latent Space of GANs for Semantic Face Editing](https://mlsanity.com/paper/1907.10786/) (2019)
- [GANSpace: Discovering Interpretable GAN Controls](https://mlsanity.com/paper/2004.02546/) (2020)
- [Closed-Form Factorization of Latent Semantics in GANs](https://mlsanity.com/paper/2007.06600/) (2020)
- [Unsupervised Discovery of Interpretable Directions in the GAN Latent Space](https://mlsanity.com/paper/2002.03754/) (2020)
- [Large Scale Adversarial Representation Learning](https://mlsanity.com/paper/1907.02544/) (2019)
- [Deep Generative Image Models using a Laplacian Pyramid of Adversarial Networks](https://mlsanity.com/paper/1506.05751/) (2015)
- [GANalyze: Toward Visual Definitions of Cognitive Image Properties](https://mlsanity.com/paper/1906.10112/) (2019)
- [TransGAN: Two Pure Transformers Can Make One Strong GAN, and That Can Scale Up](https://mlsanity.com/paper/2102.07074/) (2021)
- [A U-Net Based Discriminator for Generative Adversarial Networks](https://mlsanity.com/paper/2002.12655/) (2020)
- [BEGAN: Boundary Equilibrium Generative Adversarial Networks](https://mlsanity.com/paper/1703.10717/) (2017)
- [Instance-Conditioned GAN](https://mlsanity.com/paper/2109.05070/) (2021)
- [Semantic Hierarchy Emerges in Deep Generative Representations for Scene Synthesis](https://mlsanity.com/paper/1911.09267/) (2019)
- [Unsupervised Attention-guided Image to Image Translation](https://mlsanity.com/paper/1806.02311/) (2018)
- [Finding Mixed Nash Equilibria of Generative Adversarial Networks](https://mlsanity.com/paper/1811.02002/) (2018)
- [Many Paths to Equilibrium: GANs Do Not Need to Decrease a Divergence At Every Step](https://mlsanity.com/paper/1710.08446/) (2017)

## Built on by (most cited first, 22 of 22)

- [Drag Your GAN: Interactive Point-based Manipulation on the Generative Image Manifold](https://mlsanity.com/paper/2305.10973/) (2023)
- [MoVQ: Modulating Quantized Vectors for High-Fidelity Image Generation](https://mlsanity.com/paper/2209.09002/) (2022)
- [DisCoScene: Spatially Disentangled Generative Radiance Fields for Controllable 3D-aware Scene Synthesis](https://mlsanity.com/paper/2212.11984/) (2022)
- [BlobGAN: Spatially Disentangled Scene Representations](https://mlsanity.com/paper/2205.02837/) (2022)
- [Toward 3D Spatial Reasoning for Human-like Text-based Visual Question Answering](https://mlsanity.com/paper/2209.10326/) (2022)
- [DiffUHaul: A Training-Free Method for Object Dragging in Images](https://mlsanity.com/paper/2406.01594/) (2024)
- [Improving GANs with A Dynamic Discriminator](https://mlsanity.com/paper/2209.09897/) (2022)
- [A Survey on Deep Generative 3D-aware Image Synthesis](https://mlsanity.com/paper/2210.14267/) (2022)
- [Next Steps for Human-Centered Generative AI: A Technical Perspective](https://mlsanity.com/paper/2306.15774/) (2023)
- [Move Anything with Layered Scene Diffusion](https://mlsanity.com/paper/2404.07178/) (2024)
- [Physics-informed Generalizable Wireless Channel Modeling with Segmentation and Deep Learning: Fundamentals, Methodologies, and Challenges](https://mlsanity.com/paper/2401.01288/) (2024)
- [Revisiting the Evaluation of Image Synthesis with GANs](https://mlsanity.com/paper/2304.01999/) (2023)
- [A Novel Generator with Auxiliary Branch for Improving GAN Performance](https://mlsanity.com/paper/2112.14968/) (2021)
- [GLeaD: Improving GANs with A Generator-Leading Task](https://mlsanity.com/paper/2212.03752/) (2022)
- [Stabilizing GANs' Training with Brownian Motion Controller](https://mlsanity.com/paper/2306.10468/) (2023)
- [BerfScene: Bev-conditioned Equivariant Radiance Fields for Infinite 3D Scene Generation](https://mlsanity.com/paper/2312.02136/) (2023)
- [Singular Value Scaling: Efficient Generative Model Compression via Pruned Weights Refinement](https://mlsanity.com/paper/2412.17387/) (2024)
- [PRISM: Privacy-Preserving Improved Stochastic Masking for Federated Generative Models](https://mlsanity.com/paper/2503.08085/) (2025)
- [Spatial Steerability of GANs via Self-Supervision from Discriminator](https://mlsanity.com/paper/2301.08455/) (2023)
- [Learning Modulated Transformation in GANs](https://mlsanity.com/paper/2308.15472/) (2023)
- [AACP: Aesthetics assessment of children's paintings based on self-supervised learning](https://mlsanity.com/paper/2403.07578/) (2024)
- [UCD: Unconditional Discriminator Promotes Nash Equilibrium in GANs](https://mlsanity.com/paper/2510.00624/) (2025)

## Abstract (arXiv)

The success of Generative Adversarial Networks (GANs) is largely built upon the adversarial training between a generator (G) and a discriminator (D). They are expected to reach a certain equilibrium where D cannot distinguish the generated images from the real ones. However, such an equilibrium is rarely achieved in practical GAN training, instead, D almost always surpasses G. We attribute one of its sources to the information asymmetry between D and G. We observe that D learns its own visual attention when determining whether an image is real or fake, but G has no explicit clue on which regions to focus on for a particular synthesis. To alleviate the issue of D dominating the competition in GANs, we aim to raise the spatial awareness of G. Randomly sampled multi-level heatmaps are encoded into the intermediate layers of G as an inductive bias. Thus G can purposefully improve the synthesis of certain image regions. We further propose to align the spatial awareness of G with the attention map induced from D. Through this way we effectively lessen the information gap between D and G. Extensive results show that our method pushes the two-player game in GANs closer to the equilibrium, leading to a better synthesis performance. As a byproduct, the introduced spatial awareness facilitates interactive editing over the output synthesis. Demo video and code are available at https://genforce.github.io/eqgan-sa/.