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
Logistic-Normal Likelihoods for Heteroscedastic Label Noise
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: 0000-0002-6193-7126
KTH, School of Electrical Engineering and Computer Science (EECS), Intelligent systems, Robotics, Perception and Learning, RPL.ORCID iD: 0000-0001-5211-6388
2023 (English)In: Transactions on Machine Learning Research, E-ISSN 2835-8856, Vol. 2023, no 8Article in journal (Refereed) Published
Abstract [en]

A natural way of estimating heteroscedastic label noise in regression is to model the observed (potentially noisy) target as a sample from a normal distribution, whose parameters can be learned by minimizing the negative log-likelihood. This formulation has desirable loss attenuation properties, as it reduces the contribution of high-error examples. Intuitively, this behavior can improve robustness against label noise by reducing overfitting. We propose an extension of this simple and probabilistic approach to classification that has the same desirable loss attenuation properties. Furthermore, we discuss and address some practical challenges of this extension. We evaluate the effectiveness of the method by measuring its robustness against label noise in classification. We perform enlightening experiments exploring the inner workings of the method, including sensitivity to hyperparameters, ablation studies, and other insightful analyses.

Place, publisher, year, edition, pages
Transactions on Machine Learning Research (TMLR) , 2023. Vol. 2023, no 8
National Category
Computer Sciences
Identifiers
URN: urn:nbn:se:kth:diva-346451Scopus ID: 2-s2.0-86000109470OAI: oai:DiVA.org:kth-346451DiVA, id: diva2:1857950
Funder
Wallenberg AI, Autonomous Systems and Software Program (WASP)
Note

QC 20250325

Available from: 2024-05-15 Created: 2024-05-15 Last updated: 2025-03-25Bibliographically 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(2963 kB)88 downloads
File information
File name FULLTEXT01.pdfFile size 2963 kBChecksum SHA-512
32c041a8de2775b0bd9c67d0ca47eb57fae0273aa433565abe0dc8b9b8b96efe760ea1b95cb58eea2f6368cf375341f469d1e596e5104faf802ed8466dabb656
Type fulltextMimetype application/pdf

Other links

ScopusPaperCode

Authority records

Englesson, ErikMehrpanah, AmirAzizpour, Hossein

Search in DiVA

By author/editor
Englesson, ErikMehrpanah, AmirAzizpour, Hossein
By organisation
Robotics, Perception and Learning, RPL
In the same journal
Transactions on Machine Learning Research
Computer Sciences

Search outside of DiVA

GoogleGoogle Scholar
Total: 88 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: 290 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