mlsanityData to 7 Oct 2026

ITTR: Unpaired Image-to-Image Translation with Transformers

arXiv 2203.16015 ↗First posted 30 Mar 2022cs.CVcited by 15

Not on the map. Why?

Abstract (arXiv)

Unpaired image-to-image translation is to translate an image from a source domain to a target domain without paired training data. By utilizing CNN in extracting local semantics, various techniques have been developed to improve the translation performance. However, CNN-based generators lack the ability to capture long-range dependency to well exploit global semantics. Recently, Vision Transformers have been widely investigated for recognition tasks. Though appealing, it is inappropriate to simply transfer a recognition-based vision transformer to image-to-image translation due to the generation difficulty and the computation limitation. In this paper, we propose an effective and efficient architecture for unpaired Image-to-Image Translation with Transformers (ITTR). It has two main designs: 1) hybrid perception block (HPB) for token mixing from different receptive fields to utilize global semantics; 2) dual pruned self-attention (DPSA) to sharply reduce the computational complexity. Our ITTR outperforms the state-of-the-arts for unpaired image-to-image translation on six benchmark datasets.

Key facts. Cited by 15 papers in the map (data through 7 Oct 2026). Builds on 52 of its 58 references that are in the map. First posted on arXiv 30 Mar 2022.

Builds on

52 of 58 references.

References · 52

  1. 2017Attention Is All You Needcited by 59,932
  2. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  3. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  4. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 29,915
  5. 2021Swin Transformer: Hierarchical Vision Transformer using Shifted Windowscited by 12,082
  6. 2016Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localizationcited by 6,690
  7. 2018A Style-Based Generator Architecture for Generative Adversarial Networkscited by 5,986
  8. 2018MobileNetV2: Inverted Residuals and Linear Bottleneckscited by 4,773
  9. 2020Training data-efficient image transformers & distillation through attentioncited by 4,560
  10. 2016Image-to-Image Translation with Conditional Adversarial Networkscited by 4,510
  11. 2016The Cityscapes Dataset for Semantic Urban Scene Understandingcited by 4,427
  12. 2019Analyzing and Improving the Image Quality of StyleGANcited by 3,580
38 more
  1. 2016Gaussian Error Linear Units (GELUs)cited by 3,431
  2. 2017Non-local Neural Networkscited by 2,290
  3. 2021Pyramid Vision Transformer: A Versatile Backbone for Dense Prediction without Convolutionscited by 1,960
  4. 2019Semantic Image Synthesis with Spatially-Adaptive Normalizationcited by 1,295
  5. 2016Instance Normalization: The Missing Ingredient for Fast Stylizationcited by 1,187
  6. 2020Training Generative Adversarial Networks with Limited Datacited by 1,184
  7. 2017High-Resolution Image Synthesis and Semantic Manipulation with Conditional GANscited by 1,176
  8. 2021Tokens-to-Token ViT: Training Vision Transformers from Scratch on ImageNetcited by 1,096
  9. 2019StarGAN v2: Diverse Image Synthesis for Multiple Domainscited by 1,095
  10. 2021CvT: Introducing Convolutions to Vision Transformerscited by 946
  11. 2018Self-Attention Generative Adversarial Networkscited by 809
  12. 2021PVT v2: Improved Baselines with Pyramid Vision Transformercited by 749
  13. 2020Contrastive Learning for Unpaired Image-to-Image Translationcited by 637
  14. 2021MobileViT: Light-weight, General-purpose, and Mobile-friendly Vision Transformercited by 636
  15. 2017Unsupervised Image-to-Image Translation Networkscited by 602
  16. 2021Twins: Revisiting the Design of Spatial Attention in Vision Transformerscited by 565
  17. 2021LeViT: a Vision Transformer in ConvNet's Clothing for Faster Inferencecited by 475
  18. 2021Rethinking Spatial Dimensions of Vision Transformerscited by 361
  19. 2021CMT: Convolutional Neural Networks Meet Vision Transformerscited by 310
  20. 2017Dilated Residual Networkscited by 293
  21. 2017Learning to Discover Cross-Domain Relations with Generative Adversarial Networkscited by 278
  22. 2019DRIT++: Diverse Image-to-Image Translation via Disentangled Representationscited by 244
  23. 2021Mobile-Former: Bridging MobileNet and Transformercited by 234
  24. 2017Improved Texture Networks: Maximizing Quality and Diversity in Feed-forward Stylization and Texture Synthesiscited by 215
  25. 2019U-GAT-IT: Unsupervised Generative Attentional Networks with Adaptive Layer-Instance Normalization for Image-to-Image Translationcited by 186
  26. 2021TransGAN: Two Pure Transformers Can Make One Strong GAN, and That Can Scale Upcited by 162
  27. 2021StyleSwin: Transformer-based GAN for High-resolution Image Generationcited by 152
  28. 2021HRFormer: High-Resolution Transformer for Dense Predictioncited by 149
  29. 2021Generative Adversarial Transformerscited by 120
  30. 2018Geometry-Consistent Generative Adversarial Networks for One-Sided Unsupervised Domain Mappingcited by 113
  31. 2021ViTGAN: Training GANs with Vision Transformerscited by 110
  32. 2017One-Sided Unsupervised Domain Mappingcited by 91
  33. 2021The Spatially-Correlative Loss for Various Image Translation Taskscited by 66
  34. 2021Paint Transformer: Feed Forward Neural Painting with Stroke Predictioncited by 61
  35. 2021Improved Transformer for High-Resolution GANscited by 59
  36. 2021Instance-wise Hard Negative Example Generation for Contrastive Learning in Unpaired Image-to-Image Translationcited by 45
  37. 2021Styleformer: Transformer based Generative Adversarial Networks with Style Vectorcited by 27
  38. 2021Compositional Transformers for Scene Generationcited by 24

50 most cited of 52 All 52 (JSON)

Built on by

Cited by year

Citing papers per year: 2022: 2; 2023: 5; 2024: 3; 2025: 5.

15 papers.

Sort:

By area:

  1. 2022EGSDE: Unpaired Image-to-Image Translation via Energy-Guided Stochastic Differential Equationscited by 172
  2. 2023ArtBank: Artistic Style Transfer with Pre-trained Diffusion Model and Implicit Style Prompt Bankcited by 36
  3. 2022S2WAT: Image Style Transfer via Hierarchical Vision Transformer using Strips Window Attentioncited by 14
  4. 2023Transformer-based Generative Adversarial Networks in Computer Vision: A Comprehensive Surveycited by 10
  5. 2023UVCGAN v2: An Improved Cycle-Consistent GAN for Unpaired Image-to-Image Translationcited by 8
  6. 2025CycleDiff: Cycle Diffusion Models for Unpaired Image-to-image Translationcited by 6
  7. 2025Single-Step Bidirectional Unpaired Image Translation Using Implicit Bridge Consistency Distillationcited by 4
  8. 2023Masked Discriminators for Content-Consistent Unpaired Image-to-Image Translationcited by 2
  9. 2025CSHNet: A Novel Information Asymmetric Image Translation Methodcited by 2
  10. 2024Reliable Multi-modal Medical Image-to-image Translation Independent of Pixel-wise Aligned Datacited by 1
  11. 2023Towards Unsupervised Representation Learning: Learning, Evaluating and Transferring Visual Representationscited by 0
  12. 2024Regularized Distribution Matching Distillation for One-step Unpaired Image-to-Image Translationcited by 0
3 more
  1. 2024Image class translation: visual inspection of class-specific hypotheticals and classification based on translation distancecited by 0
  2. 2025Vision Transformers for Multi-Variable Climate Downscaling: Emulating Regional Climate Models with a Shared Encoder and Multi-Decoder Architecturecited by 0
  3. 2025BrainPuzzle: Hybrid Physics and Data-Driven Reconstruction for Transcranial Ultrasound Tomographycited by 0