Twin-GAN -- Unpaired Cross-Domain Image Translation with Weight-Sharing GANs
arXiv:1809.00946
Abstract
We present a framework for translating unlabeled images from one domain into analog images in another domain. We employ a progressively growing skip-connected encoder-generator structure and train it with a GAN loss for realistic output, a cycle consistency loss for maintaining same-domain translation identity, and a semantic consistency loss that encourages the network to keep the input semantic features in the output. We apply our framework on the task of translating face images, and show that it is capable of learning semantic mappings for face images with no supervised one-to-one image mapping.
References in corpus (14)
- Adam: A Method for Stochastic Optimization
- Very Deep Convolutional Networks for Large-Scale Image Recognition
- Spectral Normalization for Generative Adversarial Networks
- Progressive Growing of GANs for Improved Quality, Stability, and Variation
- Improved Training of Wasserstein GANs
- Unsupervised Image-to-Image Translation Networks
- Unsupervised Cross-Domain Image Generation
- Modulating early visual processing by language
- Multimodal Unsupervised Image-to-Image Translation
- On Convergence and Stability of GANs
- Towards the Automatic Anime Characters Creation with Generative Adversarial Networks
- Style Transfer for Anime Sketches with Enhanced Residual U-net and Auxiliary Classifier GAN
- Visual Attribute Transfer through Deep Image Analogy
- Deep Painterly Harmonization
Cited by in corpus (7)
- Evaluating Prediction-Time Batch Normalization for Robustness under Covariate Shift
- Latent Translation: Crossing Modalities by Bridging Generative Models
- MTS-CycleGAN: An Adversarial-based Deep Mapping Learning Network for Multivariate Time Series Domain Adaptation Applied to the Ironmaking Industry
- SDIT: Scalable and Diverse Cross-domain Image Translation
- Generative Adversarial Network with Multi-Branch Discriminator for Cross-Species Image-to-Image Translation
- Auto-Encoding for Shared Cross Domain Feature Representation and Image-to-Image Translation
- One-Shot Image-to-Image Translation via Part-Global Learning with a Multi-adversarial Framework