Tensor-to-Image: Image-to-Image Translation with Vision Transformers
This addresses image-to-image translation tasks for computer vision applications, but appears incremental as it applies an existing transformer approach to this domain.
The paper tackled image-to-image translation by using a custom-designed vision transformer model called tensor-to-image, which leveraged self-attention to generalize across different problems without modifications, though no concrete results or numbers were provided.
Transformers gain huge attention since they are first introduced and have a wide range of applications. Transformers start to take over all areas of deep learning and the Vision transformers paper also proved that they can be used for computer vision tasks. In this paper, we utilized a vision transformer-based custom-designed model, tensor-to-image, for the image to image translation. With the help of self-attention, our model was able to generalize and apply to different problems without a single modification.