DeepAI AI Chat
Log In Sign Up

Fix the Noise: Disentangling Source Feature for Transfer Learning of StyleGAN

04/29/2022
by   Dongyeun Lee, et al.
0

Transfer learning of StyleGAN has recently shown great potential to solve diverse tasks, especially in domain translation. Previous methods utilized a source model by swapping or freezing weights during transfer learning, however, they have limitations on visual quality and controlling source features. In other words, they require additional models that are computationally demanding and have restricted control steps that prevent a smooth transition. In this paper, we propose a new approach to overcome these limitations. Instead of swapping or freezing, we introduce a simple feature matching loss to improve generation quality. In addition, to control the degree of source features, we train a target model with the proposed strategy, FixNoise, to preserve the source features only in a disentangled subspace of a target feature space. Owing to the disentangled feature space, our method can smoothly control the degree of the source features in a single model. Extensive experiments demonstrate that the proposed method can generate more consistent and realistic images than previous works.

READ FULL TEXT

page 8

page 9

page 10

page 11

page 12

page 14

page 15

page 16

02/01/2016

Transfer Learning Based on AdaBoost for Feature Selection from Multiple ConvNet Layer Features

Convolutional Networks (ConvNets) are powerful models that learn hierarc...
09/04/2018

Parameter Transfer Extreme Learning Machine based on Projective Model

Recent years, transfer learning has attracted much attention in the comm...
01/09/2019

Transfer Representation Learning with TSK Fuzzy System

Transfer learning can address the learning tasks of unlabeled data in th...
05/13/2021

TransferI2I: Transfer Learning for Image-to-Image Translation from Small Datasets

Image-to-image (I2I) translation has matured in recent years and is able...
07/06/2018

Towards more Reliable Transfer Learning

Multi-source transfer learning has been proven effective when within-tar...
11/27/2020

Randomized Transferable Machine

Feature-based transfer is one of the most effective methodologies for tr...
03/16/2022

CtlGAN: Few-shot Artistic Portraits Generation with Contrastive Transfer Learning

Generating artistic portraits is a challenging problem in computer visio...