Transformer Pix2Pix

I trained a transformer-based Pix2Pix GAN as a final project for CSE493G1.

We trained introduced transformers (Vaswani et al., 2017) into a standard Pix2Pix GAN (Isola et al., 2017), and experimented with four different, novel architectures. The final project report, which includes all output images, a detailed implementation, and training curves, can be found here.

References

2017

  1. Attention Is All You Need
    Ashish Vaswani, Noam Shazeer, Niki Parmar, and 5 more authors
    In Proceedings of the 31st International Conference on Neural Information Processing Systems (NIPS) , 2017
  2. Image-to-Image Translation with Conditional Adversarial Networks
    Phillip Isola, Jun-Yan Zhu, Tinghui Zhou, and 1 more author
    In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR) , 2017