# SPA-GAN: Spatial Attention GAN for Image-to-Image Translation

arXiv: https://arxiv.org/abs/1908.06616 · HTML: https://mlsanity.com/paper/1908.06616/

## Key facts

- Cited by 43 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 19 Aug 2019.

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

- [Image-to-Image Translation: Methods and Applications](https://mlsanity.com/paper/2101.08629/) (2021)
- [Image-to-image Translation via Hierarchical Style Disentanglement](https://mlsanity.com/paper/2103.01456/) (2021)
- [Diagonal Attention and Style-based GAN for Content-Style Disentanglement in Image Generation and Translation](https://mlsanity.com/paper/2103.16146/) (2021)
- [Dual-Awareness Attention for Few-Shot Object Detection](https://mlsanity.com/paper/2102.12152/) (2021)
- [A Review of Deep Learning for Video Captioning](https://mlsanity.com/paper/2304.11431/) (2023)
- [Hybrid Quantum-Classical Generative Adversarial Network for High Resolution Image Generation](https://mlsanity.com/paper/2212.11614/) (2022)
- [Diffusion Models for Contrast Harmonization of Magnetic Resonance Images](https://mlsanity.com/paper/2303.08189/) (2023)
- [Decompose to Adapt: Cross-domain Object Detection via Feature Disentanglement](https://mlsanity.com/paper/2201.01929/) (2022)
- [Diffusion Models for Time Series Forecasting: A Survey](https://mlsanity.com/paper/2507.14507/) (2025)
- [MixerGAN: An MLP-Based Architecture for Unpaired Image-to-Image Translation](https://mlsanity.com/paper/2105.14110/) (2021)
- [Region-aware Knowledge Distillation for Efficient Image-to-Image Translation](https://mlsanity.com/paper/2205.12451/) (2022)
- [RDFC-GAN: RGB-Depth Fusion CycleGAN for Indoor Depth Completion](https://mlsanity.com/paper/2306.03584/) (2023)
- [Global-Local Image Perceptual Score (GLIPS): Evaluating Photorealistic Quality of AI-Generated Images](https://mlsanity.com/paper/2405.09426/) (2024)
- [Look ATME: The Discriminator Mean Entropy Needs Attention](https://mlsanity.com/paper/2304.09024/) (2023)
- [Conditional diffusion model with spatial attention and latent embedding for medical image segmentation](https://mlsanity.com/paper/2502.06997/) (2025)
- [CycleDRUMS: Automatic Drum Arrangement For Bass Lines Using CycleGAN](https://mlsanity.com/paper/2104.00353/) (2021)
- [Asymmetric Modality Translation For Face Presentation Attack Detection](https://mlsanity.com/paper/2110.09108/) (2021)
- [Natural & Adversarial Bokeh Rendering via Circle-of-Confusion Predictive Network](https://mlsanity.com/paper/2111.12971/) (2021)
- [RFGAN: RF-Based Human Synthesis](https://mlsanity.com/paper/2112.03727/) (2021)
- [Efficient High-Resolution Image-to-Image Translation using Multi-Scale Gradient U-Net](https://mlsanity.com/paper/2105.13067/) (2021)
- [Learning Stage-wise GANs for Whistle Extraction in Time-Frequency Spectrograms](https://mlsanity.com/paper/2304.02714/) (2023)
- [Separating Content and Style for Unsupervised Image-to-Image Translation](https://mlsanity.com/paper/2110.14404/) (2021)
- [ChildPredictor: A Child Face Prediction Framework with Disentangled Learning](https://mlsanity.com/paper/2204.09962/) (2022)
- [Disentangled Generation Network for Enlarged License Plate Recognition and A Unified Dataset](https://mlsanity.com/paper/2206.00859/) (2022)
- [Guided Image-to-Image Translation by Discriminator-Generator Communication](https://mlsanity.com/paper/2303.03598/) (2023)
- [DuDGAN: Improving Class-Conditional GANs via Dual-Diffusion](https://mlsanity.com/paper/2305.14849/) (2023)
- [Hierarchical Conditional Tabular GAN for Multi-Tabular Synthetic Data Generation](https://mlsanity.com/paper/2411.07009/) (2024)
- [Identity Preserving Latent Diffusion for Brain Aging Modeling](https://mlsanity.com/paper/2503.09634/) (2025)
- [Ebola Optimization Search Algorithm (EOSA): A new metaheuristic algorithm based on the propagation model of Ebola virus disease](https://mlsanity.com/paper/2106.01416/) (2021)
- [LEA-Net: Layer-wise External Attention Network for Efficient Color Anomaly Detection](https://mlsanity.com/paper/2109.05493/) (2021)

## Abstract (arXiv)

Image-to-image translation is to learn a mapping between images from a source domain and images from a target domain. In this paper, we introduce the attention mechanism directly to the generative adversarial network (GAN) architecture and propose a novel spatial attention GAN model (SPA-GAN) for image-to-image translation tasks. SPA-GAN computes the attention in its discriminator and use it to help the generator focus more on the most discriminative regions between the source and target domains, leading to more realistic output images. We also find it helpful to introduce an additional feature map loss in SPA-GAN training to preserve domain specific features during translation. Compared with existing attention-guided GAN models, SPA-GAN is a lightweight model that does not need additional attention networks or supervision. Qualitative and quantitative comparison against state-of-the-art methods on benchmark datasets demonstrates the superior performance of SPA-GAN.