Powers of layers for image-to-image translation
arXiv:2008.05763
Abstract
We propose a simple architecture to address unpaired image-to-image translation tasks: style or class transfer, denoising, deblurring, deblocking, etc. We start from an image autoencoder architecture with fixed weights. For each task we learn a residual block operating in the latent space, which is iteratively called until the target domain is reached. A specific training schedule is required to alleviate the exponentiation effect of the iterations. At test time, it offers several advantages: the number of weight parameters is limited and the compositional design allows one to modulate the strength of the transformation with the number of iterations. This is useful, for instance, when the type or amount of noise to suppress is not known in advance. Experimentally, we provide proofs of concepts showing the interest of our method for many transformations. The performance of our model is comparable or better than CycleGAN with significantly fewer parameters.
References in corpus (6)
- Deep Compression: Compressing Deep Neural Networks with Pruning, Trained Quantization and Huffman Coding
- Large Scale GAN Training for High Fidelity Natural Image Synthesis
- YFCC100M: The New Data in Multimedia Research
- Domain Separation Networks
- fastMRI: An Open Dataset and Benchmarks for Accelerated MRI
- StyleGAN2 Distillation for Feed-forward Image Manipulation