A Plug-in Method for Representation Factorization in Connectionist Models

Jee Seok Yoon, Myung Cheol Roh, Heung Il Suk

Research output: Contribution to journalArticlepeer-review

Abstract

In this article, we focus on decomposing latent representations in generative adversarial networks or learned feature representations in deep autoencoders into semantically controllable factors in a semisupervised manner, without modifying the original trained models. Particularly, we propose factors' decomposer-entangler network (FDEN) that learns to decompose a latent representation into mutually independent factors. Given a latent representation, the proposed framework draws a set of interpretable factors, each aligned to independent factors of variations by minimizing their total correlation in an information-theoretic means. As a plug-in method, we have applied our proposed FDEN to the existing networks of adversarially learned inference and pioneer network and performed computer vision tasks of image-to-image translation in semantic ways, e.g., changing styles, while keeping the identity of a subject, and object classification in a few-shot learning scheme. We have also validated the effectiveness of the proposed method with various ablation studies in the qualitative, quantitative, and statistical examination.

Original languageEnglish
Pages (from-to)3792-3803
Number of pages12
JournalIEEE Transactions on Neural Networks and Learning Systems
Volume33
Issue number8
DOIs
Publication statusPublished - 2022 Aug 1

Keywords

  • Factorization
  • few-shot learning
  • image-to-image translation
  • mutual information
  • representation learning
  • style transfer

ASJC Scopus subject areas

  • Software
  • Computer Science Applications
  • Computer Networks and Communications
  • Artificial Intelligence

Fingerprint

Dive into the research topics of 'A Plug-in Method for Representation Factorization in Connectionist Models'. Together they form a unique fingerprint.

Cite this