kth.sePublications
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
Robust Classification via Regression for Learning with Noisy Labels
KTH, School of Electrical Engineering and Computer Science (EECS), Intelligent systems, Robotics, Perception and Learning, RPL.ORCID iD: 0000-0003-4535-2520
KTH, School of Electrical Engineering and Computer Science (EECS), Intelligent systems, Robotics, Perception and Learning, RPL.ORCID iD: 0000-0001-5211-6388
2024 (English)In: Proceedings ICLR 2024 - The Twelfth International Conference on Learning Representations, 2024Conference paper, Poster (with or without abstract) (Refereed)
Abstract [en]

Deep neural networks and large-scale datasets have revolutionized the field of machine learning. However, these large networks are susceptible to overfitting to label noise, resulting in reduced generalization. To address this challenge, two promising approaches have emerged: i) loss reweighting, which reduces the influence of noisy examples on the training loss, and ii) label correction that replaces noisy labels with estimated true labels. These directions have been pursued separately or combined as independent methods, lacking a unified approach. In this work, we present a unified method that seamlessly combines loss reweighting and label correction to enhance robustness against label noise in classification tasks. Specifically, by leveraging ideas from compositional data analysis in statistics, we frame the problem as a regression task, where loss reweighting and label correction can naturally be achieved with a shifted Gaussian label noise model. Our unified approach achieves strong performance compared to recent baselines on several noisy labelled datasets. We believe this work is a promising step towards robust deep learning in the presence of label noise. Our code is available at: https://github.com/ErikEnglesson/SGN.

Place, publisher, year, edition, pages
2024.
Keywords [en]
label noise, noisy labels, robustness, Gaussian noise, classification, log-ratio transform, compositional data analysis
National Category
Computer Sciences
Identifiers
URN: urn:nbn:se:kth:diva-346452OAI: oai:DiVA.org:kth-346452DiVA, id: diva2:1857944
Conference
ICLR 2024 - The Twelfth International Conference on Learning Representations, Messe Wien Exhibition and Congress Center, Vienna, Austria, May 7-11t, 2024 
Note

QC 20240515

Available from: 2024-05-15 Created: 2024-05-15 Last updated: 2024-05-16Bibliographically approved
In thesis
1. On Label Noise in Image Classification: An Aleatoric Uncertainty Perspective
Open this publication in new window or tab >>On Label Noise in Image Classification: An Aleatoric Uncertainty Perspective
2024 (English)Doctoral thesis, comprehensive summary (Other academic)
Abstract [en]

Deep neural networks and large-scale datasets have revolutionized the field of machine learning. However, these large networks are susceptible to overfitting to label noise, resulting in generalization degradation. In response, the thesis closely examines the problem both from an empirical and theoretical perspective. We empirically analyse the input smoothness of networks as they overfit to label noise, and we theoretically explore the connection to aleatoric uncertainty. These analyses improve our understanding of the problem and have led to our novel methods aimed at enhancing robustness against label noise in classification.

Abstract [sv]

Djupa neurala nätverk och storskaliga dataset har revolutionerat maskininlärningsområdet. Dock är dessa stora nätverk känsliga för överanpassning till felmarkerade etiketter, vilket leder till försämrad generalisering. Som svar på detta undersöker avhandlingen noggrant problemet både från en empirisk och teoretisk synvinkel. Vi analyserar empiriskt nätverkens känslighet försmå ändringar i indatan när de över anpassar till felmarkerade etiketter, och vi utforskar teoretiskt kopplingen till aleatorisk osäkerhet. Dessa analyser förbättrar vår förståelse av problemet och har lett till våra nya metoder med syfte att vara robusta mot felmarkerade etiketter i klassificering.

Place, publisher, year, edition, pages
Stockholm: KTH Royal Institute of Technology, 2024. p. xi, 68
Series
TRITA-EECS-AVL ; 2024:45
Keywords
Label noise, aleatoric uncertainty, noisy labels, robustness, etikettbrus, osäkerhet, felmarkerade etiketter, robusthet
National Category
Computer Sciences
Research subject
Computer Science
Identifiers
urn:nbn:se:kth:diva-346453 (URN)978-91-8040-925-4 (ISBN)
Public defence
2024-06-03, https://kth-se.zoom.us/w/61097277235, F3 (Flodis), Lindstedsvägen 26 & 28, Stockholm, 09:00 (English)
Opponent
Supervisors
Funder
Wallenberg AI, Autonomous Systems and Software Program (WASP)
Note

QC 20240516

Available from: 2024-05-16 Created: 2024-05-16 Last updated: 2024-06-10Bibliographically approved

Open Access in DiVA

fulltext(638 kB)439 downloads
File information
File name FULLTEXT01.pdfFile size 638 kBChecksum SHA-512
f952c89b51235c2043d98226d40f4939ca7b532da9d8e2dff03899bfd18c51d4336f03a5b32d06b4d1da01ca5b694354aa25727098c246eefd5669bcc50e4354
Type fulltextMimetype application/pdf

Other links

PaperCode

Authority records

Englesson, ErikAzizpour, Hossein

Search in DiVA

By author/editor
Englesson, ErikAzizpour, Hossein
By organisation
Robotics, Perception and Learning, RPL
Computer Sciences

Search outside of DiVA

GoogleGoogle Scholar
Total: 439 downloads
The number of downloads is the sum of all downloads of full texts. It may include eg previous versions that are now no longer available

urn-nbn

Altmetric score

urn-nbn
Total: 1837 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