# Patch-wise Graph Contrastive Learning for Image Translation

arXiv: https://arxiv.org/abs/2312.08223 · HTML: https://mlsanity.com/paper/2312.08223/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Builds on 28 of its 31 references that are in the map.
- First posted on arXiv 13 Dec 2023.

## Builds on (most cited first, 28 of 28)

- [Very Deep Convolutional Networks for Large-Scale Image Recognition](https://mlsanity.com/paper/1409.1556/) (2014)
- [Semi-Supervised Classification with Graph Convolutional Networks](https://mlsanity.com/paper/1609.02907/) (2016)
- [Representation Learning with Contrastive Predictive Coding](https://mlsanity.com/paper/1807.03748/) (2018)
- [Image-to-Image Translation with Conditional Adversarial Networks](https://mlsanity.com/paper/1611.07004/) (2016)
- [CBAM: Convolutional Block Attention Module](https://mlsanity.com/paper/1807.06521/) (2018)
- [SuperGlue: Learning Feature Matching with Graph Neural Networks](https://mlsanity.com/paper/1911.11763/) (2019)
- [Least Squares Generative Adversarial Networks](https://mlsanity.com/paper/1611.04076/) (2016)
- [Multimodal Unsupervised Image-to-Image Translation](https://mlsanity.com/paper/1804.04732/) (2018)
- [Graph U-Nets](https://mlsanity.com/paper/1905.05178/) (2019)
- [Splicing ViT Features for Semantic Appearance Transfer](https://mlsanity.com/paper/2201.00424/) (2022)
- [Vision GNN: An Image is Worth Graph of Nodes](https://mlsanity.com/paper/2206.00272/) (2022)
- [Style Transfer by Relaxed Optimal Transport and Self-Similarity](https://mlsanity.com/paper/1904.12785/) (2019)
- [Self-Supervised Transformers for Unsupervised Object Discovery using Normalized Cut](https://mlsanity.com/paper/2202.11539/) (2022)
- [Photorealistic Style Transfer via Wavelet Transforms](https://mlsanity.com/paper/1903.09760/) (2019)
- [Deep Spectral Methods: A Surprisingly Strong Baseline for Unsupervised Semantic Segmentation and Localization](https://mlsanity.com/paper/2205.07839/) (2022)
- [Topology Adaptive Graph Convolutional Networks](https://mlsanity.com/paper/1710.10370/) (2017)
- [Geometry-Consistent Generative Adversarial Networks for One-Sided Unsupervised Domain Mapping](https://mlsanity.com/paper/1809.05852/) (2018)
- [One-Sided Unsupervised Domain Mapping](https://mlsanity.com/paper/1706.00826/) (2017)
- [The Spatially-Correlative Loss for Various Image Translation Tasks](https://mlsanity.com/paper/2104.00854/) (2021)
- [Structural Entropy Guided Graph Hierarchical Pooling](https://mlsanity.com/paper/2206.13510/) (2022)
- [Instance-wise Hard Negative Example Generation for Contrastive Learning in Unpaired Image-to-Image Translation](https://mlsanity.com/paper/2108.04547/) (2021)
- [Exploring Patch-wise Semantic Relation for Contrastive Learning in Image-to-Image Translation Tasks](https://mlsanity.com/paper/2203.01532/) (2022)
- [QS-Attn: Query-Selected Attention for Contrastive Learning in I2I Translation](https://mlsanity.com/paper/2203.08483/) (2022)
- [Distilling Holistic Knowledge with Graph Neural Networks](https://mlsanity.com/paper/2108.05507/) (2021)
- [Modulated Contrast for Versatile Image Synthesis](https://mlsanity.com/paper/2203.09333/) (2022)
- [Self-Supervised Representation Learning via Latent Graph Prediction](https://mlsanity.com/paper/2202.08333/) (2022)
- [Deep geometric knowledge distillation with graphs](https://mlsanity.com/paper/1911.03080/) (2019)
- [Marginal Contrastive Correspondence for Guided Image Generation](https://mlsanity.com/paper/2204.00442/) (2022)

## Built on by (most cited first, 4 of 4)

- [Seg-CycleGAN : SAR-to-optical image translation guided by a downstream task](https://mlsanity.com/paper/2408.05777/) (2024)
- [CLICv2: Image Complexity Representation via Content Invariance Contrastive Learning](https://mlsanity.com/paper/2503.06641/) (2025)
- [Patch-Wise Hypergraph Contrastive Learning with Dual Normal Distribution Weighting for Multi-Domain Stain Transfer](https://mlsanity.com/paper/2503.09523/) (2025)
- [VLM-based Prompts as the Optimal Assistant for Unpaired Histopathology Virtual Staining](https://mlsanity.com/paper/2504.15545/) (2025)

## Abstract (arXiv)

Recently, patch-wise contrastive learning is drawing attention for the image translation by exploring the semantic correspondence between the input and output images. To further explore the patch-wise topology for high-level semantic understanding, here we exploit the graph neural network to capture the topology-aware features. Specifically, we construct the graph based on the patch-wise similarity from a pretrained encoder, whose adjacency matrix is shared to enhance the consistency of patch-wise relation between the input and the output. Then, we obtain the node feature from the graph neural network, and enhance the correspondence between the nodes by increasing mutual information using the contrastive loss. In order to capture the hierarchical semantic structure, we further propose the graph pooling. Experimental results demonstrate the state-of-art results for the image translation thanks to the semantic encoding by the constructed graphs.