This paper aims at the transferability of the zero-shot captioning for out-of-domain images. As shown in this image, we demonstrate the susceptibility of pre-trained vision-language models and large ...
This project trains an image upsampling model using PyTorch and the Microsoft DeepSpeed framework. The model is designed to increase the resolution of images by a factor of 2. For the most part this ...
Some results have been hidden because they may be inaccessible to you
Show inaccessible results
Feedback