vit_ae_plus_plus
vit_ae_plus_plus copied to clipboard
chinmay5
Code base for the paper ViT-AE++: Improving Vision Transformer Autoencoder for Self-supervised Medical Image Representations
Hi, Thanks a lot for your paper and for sharing your implementation. I would like to confirm what version of the BRATS dataset did you use? Was it the 2018...
Can you please share some details about the pretrained weights you have posted. Is this something we can use to extract embeddings on a new dataset?. If not, can you...
Hello, In you paper you had mentioned, that you have used ViT-AE++ on 3D as well as 2D images. However the ViT and autoencoder seem to be specifically written for...
Hi ! Thank you for your contribution with this paper, and for making the code readily available. I wanted to try the perceptual loss using the VGG-16 pretrained on medical...
