Efficient conditional GAN transfer with knowledge propagation across classes

Generative adversarial networks (GANs) have shown impressive results in both unconditional and conditional image generation. In recent literature, it is shown that pre-trained GANs, on a different dataset, can be transferred to improve the image generation from a small target data. The same, however...

Full description

Saved in:
Bibliographic Details
Main Authors: Shahbazi. Mohamad, HUANG, Zhiwu, Huang, PAUDEL, Danda Pani, CHHATKULI, Ajad, VAN, Gool L.
Format: text
Language:English
Published: Institutional Knowledge at Singapore Management University 2021
Subjects:
Online Access:https://ink.library.smu.edu.sg/sis_research/6260
https://ink.library.smu.edu.sg/context/sis_research/article/7263/viewcontent/Efficient_Conditional_GAN_Transfer_with_Knowledge_Propagation_across_Classes.pdf
Tags: Add Tag
No Tags, Be the first to tag this record!
Institution: Singapore Management University
Language: English
id sg-smu-ink.sis_research-7263
record_format dspace
spelling sg-smu-ink.sis_research-72632021-11-10T04:07:07Z Efficient conditional GAN transfer with knowledge propagation across classes Shahbazi. Mohamad, HUANG, Zhiwu Huang, PAUDEL, Danda Pani CHHATKULI, Ajad VAN, Gool L. Generative adversarial networks (GANs) have shown impressive results in both unconditional and conditional image generation. In recent literature, it is shown that pre-trained GANs, on a different dataset, can be transferred to improve the image generation from a small target data. The same, however, has not been well-studied in the case of conditional GANs (cGANs), which provides new opportunities for knowledge transfer compared to unconditional setup. In particular, the new classes may borrow knowledge from the related old classes, or share knowledge among themselves to improve the training. This motivates us to study the problem of efficient conditional GAN transfer with knowledge propagation across classes. To address this problem, we introduce a new GAN transfer method to explicitly propagate the knowledge from the old classes to the new classes. The key idea is to enforce the popularly used conditional batch normalization (BN) to learn the class-specific information of the new classes from that of the old classes, with implicit knowledge sharing among the new ones. This allows for an efficient knowledge propagation from the old classes to the new ones, with the BN parameters increasing linearly with the number of new classes. The extensive evaluation demonstrates the clear superiority of the proposed method over state-of-the-art competitors for efficient conditional GAN transfer tasks. 2021-06-01T07:00:00Z text application/pdf https://ink.library.smu.edu.sg/sis_research/6260 https://ink.library.smu.edu.sg/context/sis_research/article/7263/viewcontent/Efficient_Conditional_GAN_Transfer_with_Knowledge_Propagation_across_Classes.pdf http://creativecommons.org/licenses/by-nc-nd/4.0/ Research Collection School Of Computing and Information Systems eng Institutional Knowledge at Singapore Management University Databases and Information Systems
institution Singapore Management University
building SMU Libraries
continent Asia
country Singapore
Singapore
content_provider SMU Libraries
collection InK@SMU
language English
topic Databases and Information Systems
spellingShingle Databases and Information Systems
Shahbazi. Mohamad,
HUANG, Zhiwu
Huang,
PAUDEL, Danda Pani
CHHATKULI, Ajad
VAN, Gool L.
Efficient conditional GAN transfer with knowledge propagation across classes
description Generative adversarial networks (GANs) have shown impressive results in both unconditional and conditional image generation. In recent literature, it is shown that pre-trained GANs, on a different dataset, can be transferred to improve the image generation from a small target data. The same, however, has not been well-studied in the case of conditional GANs (cGANs), which provides new opportunities for knowledge transfer compared to unconditional setup. In particular, the new classes may borrow knowledge from the related old classes, or share knowledge among themselves to improve the training. This motivates us to study the problem of efficient conditional GAN transfer with knowledge propagation across classes. To address this problem, we introduce a new GAN transfer method to explicitly propagate the knowledge from the old classes to the new classes. The key idea is to enforce the popularly used conditional batch normalization (BN) to learn the class-specific information of the new classes from that of the old classes, with implicit knowledge sharing among the new ones. This allows for an efficient knowledge propagation from the old classes to the new ones, with the BN parameters increasing linearly with the number of new classes. The extensive evaluation demonstrates the clear superiority of the proposed method over state-of-the-art competitors for efficient conditional GAN transfer tasks.
format text
author Shahbazi. Mohamad,
HUANG, Zhiwu
Huang,
PAUDEL, Danda Pani
CHHATKULI, Ajad
VAN, Gool L.
author_facet Shahbazi. Mohamad,
HUANG, Zhiwu
Huang,
PAUDEL, Danda Pani
CHHATKULI, Ajad
VAN, Gool L.
author_sort Shahbazi. Mohamad,
title Efficient conditional GAN transfer with knowledge propagation across classes
title_short Efficient conditional GAN transfer with knowledge propagation across classes
title_full Efficient conditional GAN transfer with knowledge propagation across classes
title_fullStr Efficient conditional GAN transfer with knowledge propagation across classes
title_full_unstemmed Efficient conditional GAN transfer with knowledge propagation across classes
title_sort efficient conditional gan transfer with knowledge propagation across classes
publisher Institutional Knowledge at Singapore Management University
publishDate 2021
url https://ink.library.smu.edu.sg/sis_research/6260
https://ink.library.smu.edu.sg/context/sis_research/article/7263/viewcontent/Efficient_Conditional_GAN_Transfer_with_Knowledge_Propagation_across_Classes.pdf
_version_ 1770575912297824256