Bidirectional Copy-Paste for Semi-Supervised Medical Image Segmentation

In semi-supervised medical image segmentation, there exist empirical mismatch problems between labeled and un-labeled data distribution. The knowledge learned from the labeled data may be largely discarded if treating labeled and unlabeled data separately or in an inconsistent manner. We propose a straightforward method for alleviating the problem-copy-pasting labeled and unlabeled data bidirectionally, in a simple Mean Teacher architecture. The method encourages unlabeled data to learn comprehensive common semantics from the labeled data in both inward and outward directions. More importantly, the consistent learning procedure for labeled and unlabeled data can largely reduce the empirical distribution gap.…

• NS
  Natural Science Foundation of Shanghai

  Award: 21ZR1420800
• NN
  National Natural Science Foundation of China

  Award: 62101191
• SA
  Science and Technology Commission of Shanghai Municipality

  Award: 22DZ2229004
• FR
  Fundamental Research Funds for the Central Universities