{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/uvcgan-unet-vision-transformer-cycle","title":"UVCGAN: UNet Vision Transformer cycle-consistent GAN for unpaired image-to-image translation","arxiv_id":"2203.02557","date":"2022-03-04","proceeding":null,"authors":["Dmitrii Torbunov","Yi Huang","Haiwang Yu","Jin Huang","Shinjae Yoo","MeiFeng Lin","Brett Viren","Yihui Ren"],"abstract":"Unpaired image-to-image translation has broad applications in art, design, and scientific simulations. One early breakthrough was CycleGAN that emphasizes one-to-one mappings between two unpaired image domains via generative-adversarial networks (GAN) coupled with the cycle-consistency constraint, while more recent works promote one-to-many mapping to boost diversity of the translated images. Motivated by scientific simulation and one-to-one needs, this work revisits the classic CycleGAN framework and boosts its performance to outperform more contemporary models without relaxing the cycle-consistency constraint. To achieve this, we equip the generator with a Vision Transformer (ViT) and employ necessary training and regularization techniques. Compared to previous best-performing models, our model performs better and retains a strong correlation between the original and translated image. An accompanying ablation study shows that both the gradient penalty and self-supervised pre-training are crucial to the improvement. To promote reproducibility and open science, the source code, hyperparameter configurations, and pre-trained model are available at https://github.com/LS4GAN/uvcgan.","url_abs":"https://arxiv.org/abs/2203.02557v3","url_pdf":"https://arxiv.org/pdf/2203.02557v3.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"uvcgan-unet-vision-transformer-cycle","repo_url":"https://github.com/ls4gan/benchmarking","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"uvcgan-unet-vision-transformer-cycle","repo_url":"https://github.com/ls4gan/uvcgan","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"NOASSERTION"}}],"tasks":[{"task_slug":"diversity","task_name":"Diversity"},{"task_slug":"image-to-image-translation","task_name":"Image-to-Image Translation"},{"task_slug":"translation","task_name":"Translation"}],"methods":[{"method_slug":"absolute-position-encodings","method_name":"Absolute Position Encodings"},{"method_slug":"adam","method_name":"Adam"},{"method_slug":"attention","method_name":"Attention"},{"method_slug":"bpe","method_name":"BPE"},{"method_slug":"batch-normalization","method_name":"Batch Normalization"},{"method_slug":"convolution","method_name":"Convolution"},{"method_slug":"cycle-consistency-loss","method_name":"Cycle Consistency Loss"},{"method_slug":"dense-connections","method_name":"Dense Connections"},{"method_slug":"dropout","method_name":"Dropout"},{"method_slug":"gan-least-squares-loss","method_name":"GAN Least Squares Loss"},{"method_slug":"instance-normalization","method_name":"Instance Normalization"},{"method_slug":"label-smoothing","method_name":"Label Smoothing"},{"method_slug":"layer-normalization","method_name":"Layer Normalization"},{"method_slug":"linear-layer","method_name":"Linear Layer"},{"method_slug":"multi-head-attention","method_name":"Multi-Head Attention"},{"method_slug":"patchgan","method_name":"PatchGAN"},{"method_slug":"position-wise-feed-forward-layer","method_name":"Position-Wise Feed-Forward Layer"},{"method_slug":"relu","method_name":"ReLU"},{"method_slug":"residual-block","method_name":"Residual Block"},{"method_slug":"residual-connection","method_name":"Residual Connection"},{"method_slug":"sigmoid-activation","method_name":"Sigmoid Activation"},{"method_slug":"softmax","method_name":"Softmax"},{"method_slug":"tanh-activation","method_name":"Tanh Activation"},{"method_slug":"transformer","method_name":"Transformer"},{"method_slug":"vision-transformer","method_name":"Vision Transformer"}],"datasets_introduced":[{"slug":"pretrained-models-of-the-benchmarking","name":"Pretrained Models of the Benchmarking Algorithms for UVCGAN","full_name":""}],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2203.02557","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}