Data to 7 Oct 2026

Contrastive Learning for Unpaired Image-to-Image Translation

arXiv 2007.15651 ↗First posted 30 Jul 2020cs.CV cs.LGcited by 637

Not on the map. Why?

Cited by 74 in Diffusion models, but placed by its own abstract, which didn’t fit.

Abstract (arXiv)

In image-to-image translation, each patch in the output should reflect the content of the corresponding patch in the input, independent of domain. We propose a straightforward method for doing so -- maximizing mutual information between the two, using a framework based on contrastive learning. The method encourages two elements (corresponding patches) to map to a similar point in a learned feature space, relative to other elements (other patches) in the dataset, referred to as negatives. We explore several critical design choices for making contrastive learning effective in the image synthesis setting. Notably, we use a multilayer, patch-based approach, rather than operate on entire images. Furthermore, we draw negatives from within the input image itself, rather than from the rest of the dataset. We demonstrate that our framework enables one-sided translation in the unpaired image-to-image translation setting, while improving quality and reducing training time. In addition, our method can even be extended to the training setting where each "domain" is only a single image.

Key facts. Cited by 637 papers in the map (data through 7 Oct 2026). First posted on arXiv 30 Jul 2020.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 98; 2022: 143; 2023: 148; 2024: 100; 2025: 85; 2026: 63.

637 papers.

Sort:

By area:

2022Plug-and-Play Diffusion Features for Text-Driven Image-to-Image Translationcited by 897
2021ILVR: Conditioning Method for Denoising Diffusion Probabilistic Modelscited by 634
2023Zero-shot Image-to-Image Translationcited by 503
2023Scaling up GANs for Text-to-Image Synthesiscited by 492
2021Self-Supervised Pre-Training of Swin Transformers for 3D Medical Image Analysiscited by 418
2021Pose-Controllable Talking Face Generation by Implicitly Modularized Audio-Visual Representationcited by 288
2021Cross-Modal Contrastive Learning for Text-to-Image Generationcited by 259
2021Contrastive Learning for Compact Single Image Dehazingcited by 219
2021GRAM: Generative Radiance Manifolds for 3D-Aware Image Generationcited by 216
2022Splicing ViT Features for Semantic Appearance Transfercited by 209
2021StyTr2: Image Style Transfer with Transformerscited by 186
2021Unsupervised Degradation Representation Learning for Blind Super-Resolutioncited by 177

38 more

2022EGSDE: Unpaired Image-to-Image Translation via Energy-Guided Stochastic Differential Equationscited by 172
2021A Good Image Generator Is What You Need for High-Resolution Video Synthesiscited by 162
2022Diffusion-based Image Translation using Disentangled Style and Content Representationcited by 148
2023Cross-Image Attention for Zero-Shot Appearance Transfercited by 135
2024Implicit Style-Content Separation using B-LoRAcited by 135
2022NeRF-Art: Text-Driven Neural Radiance Fields Stylizationcited by 126
2021CLIFF: Contrastive Learning for Improving Faithfulness and Factuality in Abstractive Summarizationcited by 120
2021Image-to-Image Translation: Methods and Applicationscited by 116
2024One-Step Image Translation with Text-to-Image Modelscited by 111
2023Artificial Intelligence for Digital and Computational Pathologycited by 106
2021SiT: Self-supervised vIsion Transformercited by 99
2023Unpaired Image-to-Image Translation via Neural Schr"odinger Bridgecited by 96
2021SPG: Unsupervised Domain Adaptation for 3D Object Detection via Semantic Point Generationcited by 93
2022Domain Enhanced Arbitrary Image Style Transfer via Contrastive Learningcited by 93
2021Divide and Contrast: Self-supervised Learning from Uncurated Datacited by 85
2021Multimodal Conditional Image Synthesis with Product-of-Experts GANscited by 75
2021Enhancing Photorealism Enhancementcited by 74
2022Back to the Source: Diffusion-Driven Test-Time Adaptationcited by 71
2022Unifying Diffusion Models' Latent Space, with Applications to CycleDiffusion and Guidancecited by 67
2021The Spatially-Correlative Loss for Various Image Translation Taskscited by 66
2021Dual Contrastive Learning for Unsupervised Image-to-Image Translationcited by 65
2021Unpaired Deep Image Deraining Using Dual Contrastive Learningcited by 60
2021Data-Efficient Instance Generation from Instance Discriminationcited by 58
2022CrossMoDA 2021 challenge: Benchmark of Cross-Modality Domain Adaptation techniques for Vestibular Schwannoma and Cochlea Segmentationcited by 58
2023A survey on deep learning in medical image registration: new technologies, uncertainty, evaluation metrics, and beyondcited by 55
2022TAPE: Task-Agnostic Prior Embedding for Image Restorationcited by 54
2021Distilling Audio-Visual Knowledge by Compositional Contrastive Learningcited by 53
2021Multimodal Image Synthesis and Editing: The Generative AI Eracited by 52
2022STPLS3D: A Large-Scale Synthetic and Real Aerial Photogrammetry 3D Point Cloud Datasetcited by 52
2022A Closer Look at Few-shot Image Generationcited by 49
2023Contrastive Denoising Score for Text-guided Latent Diffusion Image Editingcited by 49
2021StyleAlign: Analysis and Applications of Aligned StyleGAN Modelscited by 48
2021Learning Disentangled Representations in the Imaging Domaincited by 46
2022CCPL: Contrastive Coherence Preserving Loss for Versatile Style Transfercited by 46
2023Regularized Vector Quantization for Tokenized Image Synthesiscited by 46
2021Instance-wise Hard Negative Example Generation for Contrastive Learning in Unpaired Image-to-Image Translationcited by 45
2021The Emergence of Objectness: Learning Zero-Shot Segmentation from Videoscited by 45
2022DiffStyler: Controllable Dual Diffusion for Text-Driven Image Stylizationcited by 45

50 most cited of 637 All 637 (JSON)