Few-shot Image Generation via Cross-domain Correspondence

2021/04/13 by Utkarsh Ojha, Yijun Li, Ojha, Utkarsh +11 · 13 citations
Computer Science · #Generative Adversarial Networks and Image Synthesis #Domain Adaptation and Few-Shot Learning #Advanced Image and Video Retrieval Techniques

paper · pdf · doi:10.48550/arxiv.2104.06820

Abstract

Training generative models, such as GANs, on a target domain containing limited examples (e.g., 10) can easily result in overfitting. In this work, we seek to utilize a large source domain for pretraining and transfer the diversity information from source to target. We propose to preserve the relative similarities and differences between instances in the source via a novel cross-domain distance consistency loss. To further reduce overfitting, we present an anchor-based strategy to encourage different levels of realism over different regions in the latent space. With extensive results in both photorealistic and non-photorealistic domains, we demonstrate qualitatively and quantitatively that our few-shot model automatically discovers correspondences between source and target domains and generates more diverse and realistic images than previous methods.

Cited by

• A Turn Toward Better Alignment: Few-Shot Generative Adaptation with Equivariant Feature Rotation
• StyleFusion360: View-Consistent Head Stylization via Adaptive Style Modulation
• Uni-DAD: Unified Distillation and Adaptation of Diffusion Models for Few-step Few-shot Image Generation
• AnoStyler: Text-Driven Localized Anomaly Generation via Lightweight Style Transfer
• CoLoR-GAN: Continual Few-Shot Learning with Low-Rank Adaptation in Generative Adversarial Networks
• Few-shot multi-token DreamBooth with LoRa for style-consistent character generation
• Analytical Survey of Learning with Low-Resource Data: From Analysis to Investigation
• Creative synthesis of kinematic mechanisms
• Double Helix Diffusion for Cross-Domain Anomaly Image Generation
• Styleclone: Face Stylization with Diffusion Based Data Augmentation
• Leveraging Diffusion Models for Stylization using Multiple Style Images
• Training-Free Anomaly Generation via Dual-Attention Enhancement in Diffusion Model
• Subject or Style: Adaptive and Training-Free Mixture of LoRAs

Related

• Domain Adaptation for Learning Generator from Paired Few-Shot Data
• Few-shot Image Generation with Mixup-based Distance Learning
• Peer is Your Pillar: A Data-unbalanced Conditional GANs for Few-shot Image Generation
• Few-shot Image Generation via Style Adaptation and Content Preservation
• One-Shot Generative Domain Adaptation