Check the preview of 2nd version of this platform
being developed by the open MLCommons taskforce on automation and reproducibility
as a free, open-source and technology-agnostic on-prem platform.
SingleGAN: Image-to-Image Translation by a Single-Generator Network using Multiple Generative Adversarial Learning
lib:caea72529d493aaa (v1.0.0)
Authors: Xiaoming Yu,Xing Cai,Zhenqiang Ying,Thomas Li,Ge Li
ArXiv: 1810.04991
Document: PDF DOI
Artifact development version: GitHub
Abstract URL: https://arxiv.org/abs/1810.04991v2
Image translation is a burgeoning field in computer vision where the goal is to learn the mapping between an input image and an output image. However, most recent methods require multiple generators for modeling different domain mappings, which are inefficient and ineffective on some multi-domain image translation tasks. In this paper, we propose a novel method, SingleGAN, to perform multi-domain image-to-image translations with a single generator. We introduce the domain code to explicitly control the different generative tasks and integrate multiple optimization goals to ensure the translation. Experimental results on several unpaired datasets show superior performance of our model in translation between two domains. Besides, we explore variants of SingleGAN for different tasks, including one-to-many domain translation, many-to-many domain translation and one-to-one domain translation with multimodality. The extended experiments show the universality and extensibility of our model.
ArXiv: 1810.04991
Document: PDF DOI
Artifact development version: GitHub
Abstract URL: https://arxiv.org/abs/1810.04991v2
Image translation is a burgeoning field in computer vision where the goal is to learn the mapping between an input image and an output image. However, most recent methods require multiple generators for modeling different domain mappings, which are inefficient and ineffective on some multi-domain image translation tasks. In this paper, we propose a novel method, SingleGAN, to perform multi-domain image-to-image translations with a single generator. We introduce the domain code to explicitly control the different generative tasks and integrate multiple optimization goals to ensure the translation. Experimental results on several unpaired datasets show superior performance of our model in translation between two domains. Besides, we explore variants of SingleGAN for different tasks, including one-to-many domain translation, many-to-many domain translation and one-to-one domain translation with multimodality. The extended experiments show the universality and extensibility of our model.
Relevant initiatives
Related knowledge about this paper
Reproduced results (crowd-benchmarking and competitions)
Artifact and reproducibility checklists
- ACM/cTuning artifact appendix and reproducibility checklist
- NeurIPS reproducibility checklist
- SIGPLAN's checklist for empirical evaluation
- Collective Knowledge (organizing research projects based on FAIR principles)