Patch-wise Graph Contrastive Learning for Image Translation
This work addresses image translation tasks by enhancing semantic correspondence, though it appears incremental as it builds on existing patch-wise contrastive learning methods.
The paper tackled the problem of improving semantic understanding in image translation by using graph neural networks to capture patch-wise topology, achieving state-of-the-art results.
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.