SPA-GAN: Spatial Attention GAN for Image-to-Image Translation
Not on the map. Why?
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.
Key facts. Cited by 43 papers in the map (data through 7 Oct 2026). First posted on arXiv 19 Aug 2019.
Builds on
No reference list yet.
Built on by
Citing papers per year: 2021: 14; 2022: 9; 2023: 10; 2024: 5; 2025: 5.
43 papers.
Sort:
By area:
- 2021Image-to-Image Translation: Methods and Applicationscited by 116
- 2021Image-to-image Translation via Hierarchical Style Disentanglementcited by 63
- 2021Diagonal Attention and Style-based GAN for Content-Style Disentanglement in Image Generation and Translationcited by 35
- 2021Dual-Awareness Attention for Few-Shot Object Detectioncited by 29
- 2023A Review of Deep Learning for Video Captioningcited by 28
- 2022Hybrid Quantum-Classical Generative Adversarial Network for High Resolution Image Generationcited by 22
- 2023Diffusion Models for Contrast Harmonization of Magnetic Resonance Imagescited by 19
- 2022Decompose to Adapt: Cross-domain Object Detection via Feature Disentanglementcited by 15
- 2025Diffusion Models for Time Series Forecasting: A Surveycited by 11
- 2021MixerGAN: An MLP-Based Architecture for Unpaired Image-to-Image Translationcited by 10
- 2022Region-aware Knowledge Distillation for Efficient Image-to-Image Translationcited by 10
- 2023RDFC-GAN: RGB-Depth Fusion CycleGAN for Indoor Depth Completioncited by 7
31 more
- 2024Global-Local Image Perceptual Score (GLIPS): Evaluating Photorealistic Quality of AI-Generated Imagescited by 7
- 2023Look ATME: The Discriminator Mean Entropy Needs Attentioncited by 6
- 2025Conditional diffusion model with spatial attention and latent embedding for medical image segmentationcited by 5
- 2021CycleDRUMS: Automatic Drum Arrangement For Bass Lines Using CycleGANcited by 4
- 2021Asymmetric Modality Translation For Face Presentation Attack Detectioncited by 4
- 2021Natural & Adversarial Bokeh Rendering via Circle-of-Confusion Predictive Networkcited by 4
- 2021RFGAN: RF-Based Human Synthesiscited by 4
- 2021Efficient High-Resolution Image-to-Image Translation using Multi-Scale Gradient U-Netcited by 3
- 2023Learning Stage-wise GANs for Whistle Extraction in Time-Frequency Spectrogramscited by 2
- 2021Separating Content and Style for Unsupervised Image-to-Image Translationcited by 1
- 2022ChildPredictor: A Child Face Prediction Framework with Disentangled Learningcited by 1
- 2022Disentangled Generation Network for Enlarged License Plate Recognition and A Unified Datasetcited by 1
- 2023Guided Image-to-Image Translation by Discriminator-Generator Communicationcited by 1
- 2023DuDGAN: Improving Class-Conditional GANs via Dual-Diffusioncited by 1
- 2024Hierarchical Conditional Tabular GAN for Multi-Tabular Synthetic Data Generationcited by 1
- 2025Identity Preserving Latent Diffusion for Brain Aging Modelingcited by 1
- 2021Ebola Optimization Search Algorithm (EOSA): A new metaheuristic algorithm based on the propagation model of Ebola virus diseasecited by 0
- 2021LEA-Net: Layer-wise External Attention Network for Efficient Color Anomaly Detectioncited by 0
- 2021SDA-GAN: Unsupervised Image Translation Using Spectral Domain Attention-Guided Generative Adversarial Networkcited by 0
- 2022Multi-Modality Image Super-Resolution using Generative Adversarial Networkscited by 0
- 2022Multi-Modality Image Inpainting using Generative Adversarial Networkscited by 0
- 2022Effect of Instance Normalization on Fine-Grained Control for Sketch-Based Face Image Generationcited by 0
- 2022GAMMA: Generative Augmentation for Attentive Marine Debris Detectioncited by 0
- 20233D Colored Shape Reconstruction from a Single RGB Image through Diffusioncited by 0
- 2023Exploring the Power of Generative Deep Learning for Image-to-Image Translation and MRI Reconstruction: A Cross-Domain Reviewcited by 0
- 2023High-resolution Multi-spectral Image Guided DEM Super-resolution using Sinkhorn Regularized Adversarial Networkcited by 0
- 2024TrIM, Triangular Input Movement Systolic Array for Convolutional Neural Networks: Architecture and Hardware Implementationcited by 0
- 2024A Sinkhorn Regularized Adversarial Network for Image Guided DEM Super-resolution using Frequency Selective Hybrid Graph Transformercited by 0
- 2024Enhanced Unsupervised Image-to-Image Translation Using Contrastive Learning and Histogram of Oriented Gradientscited by 0
- 2025PartStickers: Generating Parts of Objects for Rapid Prototypingcited by 0
- 2025Generative Adversarial Networks Applied for Privacy Preservation in Biometric-Based Authentication and Identificationcited by 0
- 2025Generative Adversarial Networks Applied for Privacy Preservation in Biometric-Based Authentication and Identification24 Sep 2025
- 2025Diffusion Models for Time Series Forecasting: A Survey19 Jul 2025
- 2025PartStickers: Generating Parts of Objects for Rapid Prototyping7 Apr 2025
- 2025Identity Preserving Latent Diffusion for Brain Aging Modeling11 Mar 2025
- 2025Conditional diffusion model with spatial attention and latent embedding for medical image segmentation10 Feb 2025
- 2024Hierarchical Conditional Tabular GAN for Multi-Tabular Synthetic Data Generation11 Nov 2024
- 2024Enhanced Unsupervised Image-to-Image Translation Using Contrastive Learning and Histogram of Oriented Gradients24 Sep 2024
- 2024A Sinkhorn Regularized Adversarial Network for Image Guided DEM Super-resolution using Frequency Selective Hybrid Graph Transformer21 Sep 2024
- 2024TrIM, Triangular Input Movement Systolic Array for Convolutional Neural Networks: Architecture and Hardware Implementation5 Aug 2024
- 2024Global-Local Image Perceptual Score (GLIPS): Evaluating Photorealistic Quality of AI-Generated Images15 May 2024
- 2023High-resolution Multi-spectral Image Guided DEM Super-resolution using Sinkhorn Regularized Adversarial Network27 Nov 2023
- 2023RDFC-GAN: RGB-Depth Fusion CycleGAN for Indoor Depth Completion6 Jun 2023
31 more
- 2023DuDGAN: Improving Class-Conditional GANs via Dual-Diffusion24 May 2023
- 2023A Review of Deep Learning for Video Captioning22 Apr 2023
- 2023Look ATME: The Discriminator Mean Entropy Needs Attention18 Apr 2023
- 2023Learning Stage-wise GANs for Whistle Extraction in Time-Frequency Spectrograms5 Apr 2023
- 2023Exploring the Power of Generative Deep Learning for Image-to-Image Translation and MRI Reconstruction: A Cross-Domain Review16 Mar 2023
- 2023Diffusion Models for Contrast Harmonization of Magnetic Resonance Images14 Mar 2023
- 2023Guided Image-to-Image Translation by Discriminator-Generator Communication7 Mar 2023
- 20233D Colored Shape Reconstruction from a Single RGB Image through Diffusion11 Feb 2023
- 2022Hybrid Quantum-Classical Generative Adversarial Network for High Resolution Image Generation22 Dec 2022
- 2022GAMMA: Generative Augmentation for Attentive Marine Debris Detection7 Dec 2022
- 2022Effect of Instance Normalization on Fine-Grained Control for Sketch-Based Face Image Generation17 Jul 2022
- 2022Multi-Modality Image Inpainting using Generative Adversarial Networks18 Jun 2022
- 2022Multi-Modality Image Super-Resolution using Generative Adversarial Networks18 Jun 2022
- 2022Disentangled Generation Network for Enlarged License Plate Recognition and A Unified Dataset2 Jun 2022
- 2022Region-aware Knowledge Distillation for Efficient Image-to-Image Translation25 May 2022
- 2022ChildPredictor: A Child Face Prediction Framework with Disentangled Learning21 Apr 2022
- 2022Decompose to Adapt: Cross-domain Object Detection via Feature Disentanglement6 Jan 2022
- 2021RFGAN: RF-Based Human Synthesis7 Dec 2021
- 2021Natural & Adversarial Bokeh Rendering via Circle-of-Confusion Predictive Network25 Nov 2021
- 2021Separating Content and Style for Unsupervised Image-to-Image Translation27 Oct 2021
- 2021Asymmetric Modality Translation For Face Presentation Attack Detection18 Oct 2021
- 2021SDA-GAN: Unsupervised Image Translation Using Spectral Domain Attention-Guided Generative Adversarial Network6 Oct 2021
- 2021LEA-Net: Layer-wise External Attention Network for Efficient Color Anomaly Detection12 Sep 2021
- 2021Ebola Optimization Search Algorithm (EOSA): A new metaheuristic algorithm based on the propagation model of Ebola virus disease2 Jun 2021
- 2021MixerGAN: An MLP-Based Architecture for Unpaired Image-to-Image Translation28 May 2021
- 2021Efficient High-Resolution Image-to-Image Translation using Multi-Scale Gradient U-Net27 May 2021
- 2021CycleDRUMS: Automatic Drum Arrangement For Bass Lines Using CycleGAN1 Apr 2021
- 2021Diagonal Attention and Style-based GAN for Content-Style Disentanglement in Image Generation and Translation30 Mar 2021
- 2021Image-to-image Translation via Hierarchical Style Disentanglement2 Mar 2021
- 2021Dual-Awareness Attention for Few-Shot Object Detection24 Feb 2021
- 2021Image-to-Image Translation: Methods and Applications21 Jan 2021
- 2023Diffusion Models for Contrast Harmonization of Magnetic Resonance Imagescited by 19
- 2025Diffusion Models for Time Series Forecasting: A Surveycited by 11
- 2025Conditional diffusion model with spatial attention and latent embedding for medical image segmentationcited by 5
- 2025Identity Preserving Latent Diffusion for Brain Aging Modelingcited by 1
- 20233D Colored Shape Reconstruction from a Single RGB Image through Diffusioncited by 0
- 2025Diffusion Models for Time Series Forecasting: A Survey19 Jul 2025
- 2025Identity Preserving Latent Diffusion for Brain Aging Modeling11 Mar 2025
- 2025Conditional diffusion model with spatial attention and latent embedding for medical image segmentation10 Feb 2025
- 2023Diffusion Models for Contrast Harmonization of Magnetic Resonance Images14 Mar 2023
- 20233D Colored Shape Reconstruction from a Single RGB Image through Diffusion11 Feb 2023
- 2021Image-to-Image Translation: Methods and Applicationscited by 116
- 2021Image-to-image Translation via Hierarchical Style Disentanglementcited by 63
- 2021Diagonal Attention and Style-based GAN for Content-Style Disentanglement in Image Generation and Translationcited by 35
- 2021Dual-Awareness Attention for Few-Shot Object Detectioncited by 29
- 2023A Review of Deep Learning for Video Captioningcited by 28
- 2022Hybrid Quantum-Classical Generative Adversarial Network for High Resolution Image Generationcited by 22
- 2022Decompose to Adapt: Cross-domain Object Detection via Feature Disentanglementcited by 15
- 2021MixerGAN: An MLP-Based Architecture for Unpaired Image-to-Image Translationcited by 10
- 2022Region-aware Knowledge Distillation for Efficient Image-to-Image Translationcited by 10
- 2023RDFC-GAN: RGB-Depth Fusion CycleGAN for Indoor Depth Completioncited by 7
- 2024Global-Local Image Perceptual Score (GLIPS): Evaluating Photorealistic Quality of AI-Generated Imagescited by 7
- 2023Look ATME: The Discriminator Mean Entropy Needs Attentioncited by 6
12 most cited of 38 All 38 (JSON)
- 2025Generative Adversarial Networks Applied for Privacy Preservation in Biometric-Based Authentication and Identification24 Sep 2025
- 2025PartStickers: Generating Parts of Objects for Rapid Prototyping7 Apr 2025
- 2024Hierarchical Conditional Tabular GAN for Multi-Tabular Synthetic Data Generation11 Nov 2024
- 2024Enhanced Unsupervised Image-to-Image Translation Using Contrastive Learning and Histogram of Oriented Gradients24 Sep 2024
- 2024A Sinkhorn Regularized Adversarial Network for Image Guided DEM Super-resolution using Frequency Selective Hybrid Graph Transformer21 Sep 2024
- 2024TrIM, Triangular Input Movement Systolic Array for Convolutional Neural Networks: Architecture and Hardware Implementation5 Aug 2024
- 2024Global-Local Image Perceptual Score (GLIPS): Evaluating Photorealistic Quality of AI-Generated Images15 May 2024
- 2023High-resolution Multi-spectral Image Guided DEM Super-resolution using Sinkhorn Regularized Adversarial Network27 Nov 2023
- 2023RDFC-GAN: RGB-Depth Fusion CycleGAN for Indoor Depth Completion6 Jun 2023
- 2023DuDGAN: Improving Class-Conditional GANs via Dual-Diffusion24 May 2023
- 2023A Review of Deep Learning for Video Captioning22 Apr 2023
- 2023Look ATME: The Discriminator Mean Entropy Needs Attention18 Apr 2023
12 newest of 38 All 38 (JSON)