Robust Autoencoders for Collective Corruption Removal

Taihui Li, Hengkang Wang, Le Peng, Xian'e Tang, Ju Sun

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

Robust PCA is a standard tool for learning a linear subspace in the presence of sparse corruption or rare outliers. What about robustly learning manifolds that are more realistic models for natural data, such as images? There have been several recent attempts to generalize robust PCA to manifold settings. In this paper, we propose ℓ1- and scaling-invariant ℓ1/ℓ2-robust autoencoders based on a surprisingly compact formulation built on the intuition that deep autoencoders perform manifold learning. We demonstrate on several standard image datasets that the proposed formulation significantly outperforms all previous methods in collectively removing sparse corruption, without clean images for training. Moreover, we also show that the learned manifold structures can be generalized to unseen data samples effectively.

Original languageEnglish (US)
Title of host publicationICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing, Proceedings
PublisherInstitute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)9781728163277
DOIs
StatePublished - 2023
Event48th IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 2023 - Rhodes Island, Greece
Duration: Jun 4 2023Jun 10 2023

Publication series

NameICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings
Volume2023-June
ISSN (Print)1520-6149

Conference

Conference48th IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 2023
Country/TerritoryGreece
CityRhodes Island
Period6/4/236/10/23

Bibliographical note

Publisher Copyright:
© 2023 IEEE.

Keywords

  • Denoising
  • Image Reconstruction
  • Manifold Learning
  • Robust Autoencoders
  • Sparse Corruption

Fingerprint

Dive into the research topics of 'Robust Autoencoders for Collective Corruption Removal'. Together they form a unique fingerprint.

Cite this