# DA-GAN: Instance-level Image Translation by Deep Attention Generative Adversarial Networks (with Supplementary Materials)

arXiv: https://arxiv.org/abs/1802.06454 · HTML: https://mlsanity.com/paper/1802.06454/

## Key facts

- Cited by 21 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 18 Feb 2018.

## Built on by (most cited first, 21 of 21)

- [DiffEdit: Diffusion-based semantic image editing with mask guidance](https://mlsanity.com/paper/2210.11427/) (2022)
- [Image-to-Image Translation: Methods and Applications](https://mlsanity.com/paper/2101.08629/) (2021)
- [Attention, please! A survey of Neural Attention Models in Deep Learning](https://mlsanity.com/paper/2103.16775/) (2021)
- [Glance and Focus Networks for Dynamic Visual Recognition](https://mlsanity.com/paper/2201.03014/) (2022)
- [Cascaded Cross MLP-Mixer GANs for Cross-View Image Translation](https://mlsanity.com/paper/2110.10183/) (2021)
- [Weather GAN: Multi-Domain Weather Translation Using Generative Adversarial Networks](https://mlsanity.com/paper/2103.05422/) (2021)
- [Generative Flows with Invertible Attentions](https://mlsanity.com/paper/2106.03959/) (2021)
- [Comparison and Analysis of Image-to-Image Generative Adversarial Networks: A Survey](https://mlsanity.com/paper/2112.12625/) (2021)
- [Physics-informed Guided Disentanglement in Generative Networks](https://mlsanity.com/paper/2107.14229/) (2021)
- [Text-to-Image Cross-Modal Generation: A Systematic Review](https://mlsanity.com/paper/2401.11631/) (2024)
- [Panoptic-aware Image-to-Image Translation](https://mlsanity.com/paper/2112.01926/) (2021)
- [Mutual-GAN: Towards Unsupervised Cross-Weather Adaptation with Mutual Information Constraint](https://mlsanity.com/paper/2106.16000/) (2021)
- [Leveraging Local Domains for Image-to-Image Translation](https://mlsanity.com/paper/2109.04468/) (2021)
- [Ownership Protection of Generative Adversarial Networks](https://mlsanity.com/paper/2306.05233/) (2023)
- [Analysis and evaluation of Deep Learning based Super-Resolution algorithms to improve performance in Low-Resolution Face Recognition](https://mlsanity.com/paper/2101.10845/) (2021)
- [MOC-GAN: Mixing Objects and Captions to Generate Realistic Images](https://mlsanity.com/paper/2106.03128/) (2021)
- [Unrealistic Feature Suppression for Generative Adversarial Networks](https://mlsanity.com/paper/2107.11047/) (2021)
- [Review Neural Networks about Image Transformation Based on IGC Learning Framework with Annotated Information](https://mlsanity.com/paper/2206.10155/) (2022)
- [On Unsupervised Image-to-image translation and GAN stability](https://mlsanity.com/paper/2403.09646/) (2023)
- [TC-PDM: Temporally Consistent Patch Diffusion Models for Infrared-to-Visible Video Translation](https://mlsanity.com/paper/2408.14227/) (2024)
- [ADROIT: A Self-Supervised Framework for Learning Robust Representations for Active Learning](https://mlsanity.com/paper/2503.07506/) (2025)

## Abstract (arXiv)

Unsupervised image translation, which aims in translating two independent sets of images, is challenging in discovering the correct correspondences without paired data. Existing works build upon Generative Adversarial Network (GAN) such that the distribution of the translated images are indistinguishable from the distribution of the target set. However, such set-level constraints cannot learn the instance-level correspondences (e.g. aligned semantic parts in object configuration task). This limitation often results in false positives (e.g. geometric or semantic artifacts), and further leads to mode collapse problem. To address the above issues, we propose a novel framework for instance-level image translation by Deep Attention GAN (DA-GAN). Such a design enables DA-GAN to decompose the task of translating samples from two sets into translating instances in a highly-structured latent space. Specifically, we jointly learn a deep attention encoder, and the instancelevel correspondences could be consequently discovered through attending on the learned instance pairs. Therefore, the constraints could be exploited on both set-level and instance-level. Comparisons against several state-ofthe- arts demonstrate the superiority of our approach, and the broad application capability, e.g, pose morphing, data augmentation, etc., pushes the margin of domain translation problem.