Digitala Vetenskapliga Arkivet

Change search
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf
Enhancing Representation Learning with Deep Classifiers in Presence of Shortcut
Linköping University, Department of Computer and Information Science, The Division of Statistics and Machine Learning. Linköping University, Faculty of Science & Engineering.ORCID iD: 0000-0001-7411-2177
Linköping University, Department of Electrical Engineering, Automatic Control. Linköping University, Department of Computer and Information Science, The Division of Statistics and Machine Learning. Linköping University, Faculty of Science & Engineering.ORCID iD: 0000-0003-3749-5820
2023 (English)In: Proceedings of IEEE ICASSP 2023, 2023Conference paper, Published paper (Refereed)
Abstract [en]

A deep neural classifier trained on an upstream task can be leveraged to boost the performance of another classifier in a related downstream task through the representations learned in hidden layers. However, presence of shortcuts (easy-to-learn features) in the upstream task can considerably impair the versatility of intermediate representations and, in turn, the downstream performance. In this paper, we propose a method to improve the representations learned by deep neural image classifiers in spite of a shortcut in upstream data. In our method, the upstream classification objective is augmented with a type of adversarial training where an auxiliary network, so called lens, fools the classifier by exploiting the shortcut in reconstructing images. Empirical comparisons in self-supervised and transfer learning problems with three shortcut-biased datasets suggest the advantages of our method in terms of downstream performance and/or training time.

Place, publisher, year, edition, pages
2023.
Keywords [en]
Deep Representation Learning, Shortcut Learning, Transfer Learning, Adversarial Methods, Computer Vision
National Category
Computer Sciences Computer Vision and Robotics (Autonomous Systems)
Identifiers
URN: urn:nbn:se:liu:diva-198763DOI: 10.1109/ICASSP49357.2023.10096346OAI: oai:DiVA.org:liu-198763DiVA, id: diva2:1807482
Conference
2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)
Available from: 2023-10-26 Created: 2023-10-26 Last updated: 2023-11-01

Open Access in DiVA

No full text in DiVA

Other links

Publisher's full text

Search in DiVA

By author/editor
Ahmadian, AmirhosseinLindsten, Fredrik
By organisation
The Division of Statistics and Machine LearningFaculty of Science & EngineeringAutomatic Control
Computer SciencesComputer Vision and Robotics (Autonomous Systems)

Search outside of DiVA

GoogleGoogle Scholar

doi
urn-nbn

Altmetric score

doi
urn-nbn
Total: 127 hits
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf