[[Paper]](https://arxiv.org/abs/2503.11591) [[Project Page]](https://histodiffusion.github.io/docs/projects/pathae/)

## DC-AE-f32-c32 finetuned on digital histopathology images.

The original autoencoder is taken from [DC-AE](https://huggingface.co/mit-han-lab/dc-ae-f32c32-in-1.0).

We fine-tune the decoder on histopathology images using an L1 reconstruction loss, a PatchGAN adversarial loss and a pathology-specific perceptual loss ([UNI](https://huggingface.co/MahmoodLab/UNI)).