Patch-wise Graph Contrastive Learning for Image Translation

TL;DR

This paper introduces a graph neural network approach to patch-wise contrastive learning for image translation, enhancing semantic understanding and achieving state-of-the-art results by capturing hierarchical structures.

Contribution

It proposes a novel graph-based method to model patch-wise topology and hierarchical semantics in image translation, improving semantic correspondence and translation quality.

Findings

Achieves state-of-the-art performance in image translation tasks.

Effectively captures hierarchical semantic structures.

Enhances patch-wise relation consistency between input and output.

Abstract

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.