mlsanityData to 7 Oct 2026

Exploring Patch-wise Semantic Relation for Contrastive Learning in Image-to-Image Translation Tasks

arXiv 2203.01532 ↗First posted 3 Mar 2022cs.CVcited by 42

Not on the map. Why?

Abstract (arXiv)

Recently, contrastive learning-based image translation methods have been proposed, which contrasts different spatial locations to enhance the spatial correspondence. However, the methods often ignore the diverse semantic relation within the images. To address this, here we propose a novel semantic relation consistency (SRC) regularization along with the decoupled contrastive learning, which utilize the diverse semantics by focusing on the heterogeneous semantics between the image patches of a single image. To further improve the performance, we present a hard negative mining by exploiting the semantic relation. We verified our method for three tasks: single-modal and multi-modal image translations, and GAN compression task for image translation. Experimental results confirmed the state-of-art performance of our method in all the three tasks.

Key facts. Cited by 42 papers in the map (data through 7 Oct 2026). Builds on 33 of its 41 references that are in the map. First posted on arXiv 3 Mar 2022.

Builds on

33 of 41 references.

References · 33

  1. 2020A Simple Framework for Contrastive Learning of Visual Representationscited by 11,979
  2. 2018The Unreasonable Effectiveness of Deep Features as a Perceptual Metriccited by 11,029
  3. 2019Momentum Contrast for Unsupervised Visual Representation Learningcited by 7,482
  4. 2020Improved Baselines with Momentum Contrastive Learningcited by 2,282
  5. 2019Contrastive Multiview Codingcited by 1,297
  6. 2019StarGAN v2: Diverse Image Synthesis for Multiple Domainscited by 1,095
  7. 2019Relational Knowledge Distillationcited by 873
  8. 2018Multimodal Unsupervised Image-to-Image Translationcited by 795
  9. 2019Once-for-All: Train One Network and Specialize it for Efficient Deploymentcited by 778
  10. 2019Contrastive Representation Distillationcited by 734
  11. 2019Learning Representations by Maximizing Mutual Information Across Viewscited by 733
  12. 2020Contrastive Learning for Unpaired Image-to-Image Translationcited by 637
21 more
  1. 2020Prototypical Contrastive Learning of Unsupervised Representationscited by 636
  2. 2020Contrastive Learning with Hard Negative Samplescited by 619
  3. 2017Unsupervised Image-to-Image Translation Networkscited by 602
  4. 2017Dilated Residual Networkscited by 293
  5. 2019Correlation Congruence for Knowledge Distillationcited by 280
  6. 2019DRIT++: Diverse Image-to-Image Translation via Disentangled Representationscited by 244
  7. 2019Style Transfer by Relaxed Optimal Transport and Self-Similaritycited by 167
  8. 2019Photorealistic Style Transfer via Wavelet Transformscited by 166
  9. 2020Knowledge Distillation Meets Self-Supervisioncited by 142
  10. 2021Decoupled Contrastive Learningcited by 141
  11. 2018Geometry-Consistent Generative Adversarial Networks for One-Sided Unsupervised Domain Mappingcited by 113
  12. 2017One-Sided Unsupervised Domain Mappingcited by 91
  13. 2020AdCo: Adversarial Contrast for Efficient Learning of Unsupervised Representations from Self-Trained Negative Adversariescited by 90
  14. 2021The Spatially-Correlative Loss for Various Image Translation Taskscited by 66
  15. 2021Instance-wise Hard Negative Example Generation for Contrastive Learning in Unpaired Image-to-Image Translationcited by 45
  16. 2021Complementary Relation Contrastive Distillationcited by 42
  17. 2021Mutual Contrastive Learning for Visual Representation Learningcited by 42
  18. 2020CO2: Consistent Contrast for Unsupervised Visual Representation Learningcited by 38
  19. 2017ComboGAN: Unrestrained Scalability for Image Domain Translationcited by 37
  20. 2019TraVeLGAN: Image-to-image Translation by Transformation Vector Learningcited by 35
  21. 2021Simpler, Faster, Stronger: Breaking The log-K Curse On Contrastive Learners With FlatNCEcited by 22

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 6; 2023: 15; 2024: 14; 2025: 4; 2026: 3.

42 papers.

Sort:

By area:

  1. 2022Diffusion-based Image Translation using Disentangled Style and Content Representationcited by 148
  2. 2023Unpaired Image-to-Image Translation via Neural Schr"odinger Bridgecited by 96
  3. 2023FreeDrag: Feature Dragging for Reliable Point-based Image Editingcited by 28
  4. 2024StegoGAN: Leveraging Steganography for Non-Bijective Image-to-Image Translationcited by 18
  5. 2023Scenimefy: Learning to Craft Anime Scene via Semi-Supervised Image-to-Image Translationcited by 15
  6. 2023GP-UNIT: Generative Prior for Versatile Unsupervised Image-to-Image Translationcited by 9
  7. 2023Exploring Semantic Consistency in Unpaired Image Translation to Generate Data for Surgical Applicationscited by 9
  8. 2024Exploring Generative AI for Sim2Real in Driving Data Synthesiscited by 7
  9. 2024Makeup-Guided Facial Privacy Protection via Untrained Neural Network Priorscited by 7
  10. 2023One-for-All: Towards Universal Domain Translation with a Single StyleGANcited by 6
  11. 2024Every Pixel Has its Moments: Ultra-High-Resolution Unpaired Image-to-Image Translation via Dense Normalizationcited by 6
  12. 2022ROMA: Cross-Domain Region Similarity Matching for Unpaired Nighttime Infrared to Daytime Visible Video Translationcited by 5
30 more
  1. 2024Towards Identifiable Unsupervised Domain Translation: A Diversified Distribution Matching Approachcited by 5
  2. 2022Discriminator-Cooperated Feature Map Distillation for GAN Compressioncited by 4
  3. 2023Towards Pragmatic Semantic Image Synthesis for Urban Scenescited by 4
  4. 2023CryoGEM: Physics-Informed Generative Cryo-Electron Microscopycited by 4
  5. 2023Patch-wise Graph Contrastive Learning for Image Translationcited by 4
  6. 2024Training A Small Emotional Vision Language Model for Visual Art Comprehensioncited by 4
  7. 2023Diff-Oracle: Deciphering Oracle Bone Scripts with Controllable Diffusion Modelcited by 3
  8. 2024Unsupervised Variational Translator for Bridging Image Restoration and High-Level Vision Taskscited by 3
  9. 2025USIGAN: Unbalanced Self-Information Feature Transport for Weakly Paired Image IHC Virtual Stainingcited by 3
  10. 2023Unsupervised Synthetic Image Refinement via Contrastive Learning and Consistent Semantic-Structural Constraintscited by 2
  11. 2023Improving Diffusion-based Image Translation using Asymmetric Gradient Guidancecited by 2
  12. 2024Automatic Scene Generation: State-of-the-Art Techniques, Models, Datasets, Challenges, and Future Prospectscited by 2
  13. 2025CSHNet: A Novel Information Asymmetric Image Translation Methodcited by 2
  14. 2022Exploring Content Relationships for Distilling Efficient GANscited by 1
  15. 2022DSI2I: Dense Style for Unpaired Image-to-Image Translationcited by 1
  16. 2023Cross-modal Face- and Voice-style Transfercited by 1
  17. 2024An Analysis for Image-to-Image Translation and Style Transfercited by 1
  18. 2024Improving Object Detection via Local-global Contrastive Learningcited by 1
  19. 2024FashionR2R: Texture-preserving Rendered-to-Real Image Translation with Diffusion Modelscited by 1
  20. 2025CryoCCD: Conditional Cycle-consistent Diffusion with Biophysical Modeling for Cryo-EM Synthesiscited by 1
  21. 2026Image-to-Image Translation Framework Embedded with Rotation Symmetry Priorscited by 1
  22. 2022Enhancing Generative Networks for Chest Anomaly Localization through Automatic Registration-Based Unpaired-to-Pseudo-Paired Training Data Translationcited by 0
  23. 2023Disentangled Contrastive Image Translation for Nighttime Surveillancecited by 0
  24. 2023SemST: Semantically Consistent Multi-Scale Image Translation via Structure-Texture Alignmentcited by 0
  25. 2024Data-driven Camera and Lidar Simulation Models for Autonomous Driving: A Review from Generative Models to Volume Rendererscited by 0
  26. 2024Enhanced Unsupervised Image-to-Image Translation Using Contrastive Learning and Histogram of Oriented Gradientscited by 0
  27. 2024NijiGAN: Transform What You See into Anime with Contrastive Semi-Supervised Learning and Neural Ordinary Differential Equationscited by 0
  28. 2025PRINTER:Deformation-Aware Adversarial Learning for Virtual IHC Staining with In Situ Fidelitycited by 0
  29. 2026One CT Unified Model Training Framework to Rule All Scanning Protocolscited by 0
  30. 2026Domain Transfer Becomes Identifiable via a Single Alignmentcited by 0