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
- Attention Is All You NeedIn Proceedings of the 31st International Conference on Neural Information Processing Systems (NIPS) , 2017
- Image-to-Image Translation with Conditional Adversarial NetworksIn Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR) , 2017