Graphonomy: Universal Image Parsing via Graph Reasoning and Transfer
IEEE transactions on pattern analysis and machine intelligence, 2020.
Prior highly-tuned image parsing models are usually studied in a certain domain with a specific set of semantic labels and can hardly be adapted into other scenarios (e.g., sharing discrepant label granularity) without extensive re-training. Learning a single universal parsing model by unifying label annotations from different domains or ...More
Full Text (Upload PDF)
PPT (Upload PPT)