DeepAI AI Chat
Log In Sign Up

MetalGAN: Multi-Domain Label-Less Image Synthesis Using cGANs and Meta-Learning

12/05/2019
by   Tomaso Fontanini, et al.
UNIVERSITÀ DEGLI STUDI DI PARMA
54

Image synthesis is currently one of the most addressed image processing topic in computer vision and deep learning fields of study. Researchers have tackled this problem focusing their efforts on its several challenging problems, e.g. image quality and size, domain and pose changing, architecture of the networks, and so on. Above all, producing images belonging to different domains by using a single architecture is a very relevant goal for image generation. In fact, a single multi-domain network would allow greater flexibility and robustness in the image synthesis task than other approaches. This paper proposes a novel architecture and a training algorithm, which are able to produce multi-domain outputs using a single network. A small portion of a dataset is intentionally used, and there are no hard-coded labels (or classes). This is achieved by combining a conditional Generative Adversarial Network (cGAN) for image generation and a Meta-Learning algorithm for domain switch, and we called our approach MetalGAN. The approach has proved to be appropriate for solving the multi-domain problem and it is validated on facial attribute transfer, using CelebA dataset.

READ FULL TEXT

page 9

page 12

page 20

page 21

page 22

page 26

page 27

page 28

03/05/2020

Image Generation from Freehand Scene Sketches

We introduce the first method for automatic image generation from scene-...
10/22/2021

MIGS: Meta Image Generation from Scene Graphs

Generation of images from scene graphs is a promising direction towards ...
05/07/2018

Unpaired Multi-Domain Image Generation via Regularized Conditional GANs

In this paper, we study the problem of multi-domain image generation, th...
04/23/2020

Efficient Neural Architecture for Text-to-Image Synthesis

Text-to-image synthesis is the task of generating images from text descr...
06/10/2020

Speech Fusion to Face: Bridging the Gap Between Human's Vocal Characteristics and Facial Imaging

While deep learning technologies are now capable of generating realistic...
03/25/2022

Spatially Multi-conditional Image Generation

In most scenarios, conditional image generation can be thought of as an ...