A Unified Feature Disentangler for Multi-Domain Image Translation and Manipulation

Abstract

We present a novel and unified deep learning framework which is capable of learning domain-invariant representation from data across multiple domains. Realized by adversarial training with additional ability to exploit domain-specific information, the proposed network is able to perform continuous cross-domain image translation and manipulation, and produces desirable output images accordingly. In addition, the resulting feature representation exhibits superior performance of unsupervised domain adaptation, which also verifies the effectiveness of the proposed model in learning disentangled features for describing cross-domain data.

arXiv commentNIPS 2018

Cited by in corpus (45)

• Federated Adversarial Domain Adaptation
• Feature Alignment and Restoration for Domain Generalization and Adaptation
• Deep Sketch-guided Cartoon Video Inbetweening
• Image-to-Image Translation: Methods and Applications
• Attribute Guided Unpaired Image-to-Image Translation with Semi-supervised Learning
• Gradient Regularized Contrastive Learning for Continual Domain Adaptation
• Learning Cross-domain Generalizable Features by Representation Disentanglement
• Style Normalization and Restitution for Domain Generalization and Adaptation
• High-Resolution Photorealistic Image Translation in Real-Time: A Laplacian Pyramid Translation Network
• TSIT: A Simple and Versatile Framework for Image-to-Image Translation
• Unconstrained Facial Expression Transfer using Style-based Generator
• Information-based Disentangled Representation Learning for Unsupervised MR Harmonization
• DRB-GAN: A Dynamic ResBlock Generative Adversarial Network for Artistic Style Transfer
• AD-GAN: End-to-end Unsupervised Nuclei Segmentation with Aligned Disentangling Training
• Exploring Explicit Domain Supervision for Latent Space Disentanglement in Unpaired Image-to-Image Translation
• Multi-Domain Image Completion for Random Missing Input Data
• MixNMatch: Multifactor Disentanglement and Encoding for Conditional Image Generation
• Learning to Transfer: Unsupervised Meta Domain Translation
• Order-Guided Disentangled Representation Learning for Ulcerative Colitis Classification with Limited Labels
• A Plug-in Method for Representation Factorization in Connectionist Models
• Variational Feature Disentangling for Fine-Grained Few-Shot Classification
• Federated Multi-Target Domain Adaptation
• Distribution Aligned Multimodal and Multi-Domain Image Stylization
• Unsupervised Shape and Pose Disentanglement for 3D Meshes
• Learning Domain Adaptive Features with Unlabeled Domain Bridges
• Adversarial Purification through Representation Disentanglement
• Partially-Shared Variational Auto-encoders for Unsupervised Domain Adaptation with Target Shift
• Domain2Vec: Domain Embedding for Unsupervised Domain Adaptation
• One-Shot Domain Adaptation For Face Generation
• Unified cross-modality feature disentangler for unsupervised multi-domain MRI abdomen organs segmentation
• Domain Fingerprints for No-reference Image Quality Assessment
• Towards Better Understanding of Disentangled Representations via Mutual Information
• Unaligned Image-to-Sequence Transformation with Loop Consistency
• Mutual Information-based Disentangled Neural Networks for Classifying Unseen Categories in Different Domains: Application to Fetal Ultrasound Imaging
• Cross-Domain Latent Modulation for Variational Transfer Learning
• Unaligned Image-to-Image Translation by Learning to Reweight
• A Survey on Adversarial Image Synthesis
• Enhanced Separable Disentanglement for Unsupervised Domain Adaptation
• TRIP: Refining Image-to-Image Translation via Rival Preferences
• Toward Zero-Shot Unsupervised Image-to-Image Translation
• TransferI2I: Transfer Learning for Image-to-Image Translation from Small Datasets
• Character-independent font identification
• Towards Accurate Knowledge Transfer via Target-awareness Representation Disentanglement
• Cross-Domain Image Manipulation by Demonstration
• Learning a Generative Model of Cancer Metastasis