Few-shot Face Image Translation via GAN Prior Distillation

by   Ruoyu Zhao, et al.

Face image translation has made notable progress in recent years. However, when training on limited data, the performance of existing approaches significantly declines. Although some studies have attempted to tackle this problem, they either failed to achieve the few-shot setting (less than 10) or can only get suboptimal results. In this paper, we propose GAN Prior Distillation (GPD) to enable effective few-shot face image translation. GPD contains two models: a teacher network with GAN Prior and a student network that fulfills end-to-end translation. Specifically, we adapt the teacher network trained on large-scale data in the source domain to the target domain with only a few samples, where it can learn the target domain's knowledge. Then, we can achieve few-shot augmentation by generating source domain and target domain images simultaneously with the same latent codes. We propose an anchor-based knowledge distillation module that can fully use the difference between the training and the augmented data to distill the knowledge of the teacher network into the student network. The trained student network achieves excellent generalization performance with the absorption of additional knowledge. Qualitative and quantitative experiments demonstrate that our method achieves superior results than state-of-the-art approaches in a few-shot setting.


page 1

page 6

page 12

page 13

page 14

page 15

page 16

page 17


Spirit Distillation: A Model Compression Method with Multi-domain Knowledge Transfer

Recent applications pose requirements of both cross-domain knowledge tra...

One-Class Knowledge Distillation for Face Presentation Attack Detection

Face presentation attack detection (PAD) has been extensively studied by...

Progressive Network Grafting for Few-Shot Knowledge Distillation

Knowledge distillation has demonstrated encouraging performances in deep...

UGAN: Untraceable GAN for Multi-Domain Face Translation

The multi-domain image-to-image translation is received increasing atten...

Single Image Texture Translation for Data Augmentation

Recent advances in image synthesis enables one to translate images by le...

EvDistill: Asynchronous Events to End-task Learning via Bidirectional Reconstruction-guided Cross-modal Knowledge Distillation

Event cameras sense per-pixel intensity changes and produce asynchronous...

DCT-Net: Domain-Calibrated Translation for Portrait Stylization

This paper introduces DCT-Net, a novel image translation architecture fo...

Please sign up or login with your details

Forgot password? Click here to reset