Patch-wise Graph Contrastive Learning for Image Translation

arXiv:2312.08223v2 Announce Type: replace
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 …

abstract arxiv attention construct cs.cv exploit explore features graph graph neural network image images network neural network semantic topology translation type understanding wise