Peng LiuMotivation
- if we don’t have any label in the target domain, how can we train a model to do segmentation or other tasks?
- we have lots of one modality (CT) paired (labeled) data in hands. If it is possible to train a model with unsupervised learning to segment the orans from x-ray (target) images?
Solution
- train a segmentation model on CT labeled data (supervised learning)—DI2I
- use a generative model to synthesize fake-CT from X-ray (fake and real)
- then send the face-CT to DI2I for segmentation
- In short: X-ray ->Generator-> Fake CT –>DI2I
- ->Cycle-GAN for synthetic
- ->concatenate the loss from DI2I with the loss from discriminator D2
paper: https://arxiv.org/abs/1806.07201