cxr-gen-report-CLIP

You can see our final report and presentation for details.

• Dataset: IU X-ray, MIMIC-CXR (Actually, we used pretrained CLIP model with the dataset)

• Model architecture for training: ResNet18, EfficientNet-b4

• Loss functions for training: Cross Entropy Loss, CLIP directional Loss

• AdamW optimizer and 2e-3 learning rate

• Result:

  • Train Loss Plots(CE, CLIP): ,

• Reference:

  https://github.com/atimashov/cxr-report-generation (our baseline),

  https://github.com/rajpurkarlab/CXR-RePaiR (CLIP model),

  https://github.com/rinongal/StyleGAN-nada (CLIP directional Loss)