Semantics-Aware Image to Image Translation and Domain Transfer
arXiv:1904.02203
Abstract
Image to image translation is the problem of transferring an image from a source domain to a different (but related) target domain. We present a new unsupervised image to image translation technique that leverages the underlying semantic information for object transfiguration and domain transfer tasks. Specifically, we present a generative adversarial learning approach that jointly translates images and labels from a source domain to a target domain. Our main technical contribution is an encoder-decoder based network architecture that jointly encodes the image and its underlying semantics and translates both individually to the target domain. Additionally, we propose object transfiguration and cross-domain semantic consistency losses that preserve semantic labels. Through extensive experimental evaluation, we demonstrate the effectiveness of our approach as compared to the state-of-the-art methods on unsupervised image-to-image translation, domain adaptation, and object transfiguration.
References in corpus (12)
- GANs Trained by a Two Time-Scale Update Rule Converge to a Local Nash Equilibrium
- Learning Transferable Features with Deep Adaptation Networks
- Conditional Adversarial Domain Adaptation
- FCNs in the Wild: Pixel-level Adversarial and Constraint-based Adaptation
- SegAN: Adversarial Network with Multi-scale Loss for Medical Image Segmentation
- Automatic Instrument Segmentation in Robot-Assisted Surgery Using Deep Learning
- Wasserstein Distance Guided Representation Learning for Domain Adaptation
- Unsupervised Attention-guided Image to Image Translation
- Semantic-aware Grad-GAN for Virtual-to-Real Urban Scene Adaption
- Augmented Cyclic Adversarial Learning for Low Resource Domain Adaptation
- Harmonic Unpaired Image-to-image Translation
- Unsupervised Domain Adaptation using Generative Models and Self-ensembling