Endre søk
RefereraExporteraLink to record
Permanent link

Direct link
Referera
Referensformat
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Annet format
Fler format
Språk
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Annet språk
Fler språk
Utmatningsformat
  • html
  • text
  • asciidoc
  • rtf
Robust Classification via Regression for Learning with Noisy Labels
KTH, Skolan för elektroteknik och datavetenskap (EECS), Intelligenta system, Robotik, perception och lärande, RPL.ORCID-id: 0000-0003-4535-2520
KTH, Skolan för elektroteknik och datavetenskap (EECS), Intelligenta system, Robotik, perception och lärande, RPL.ORCID-id: 0000-0001-5211-6388
2024 (engelsk)Inngår i: Proceedings ICLR 2024 - The Twelfth International Conference on Learning Representations, 2024Konferansepaper, Poster (with or without abstract) (Fagfellevurdert)
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.

sted, utgiver, år, opplag, sider
2024.
Emneord [en]
label noise, noisy labels, robustness, Gaussian noise, classification, log-ratio transform, compositional data analysis
HSV kategori
Identifikatorer
URN: urn:nbn:se:kth:diva-346452OAI: oai:DiVA.org:kth-346452DiVA, id: diva2:1857944
Konferanse
ICLR 2024 - The Twelfth International Conference on Learning Representations, Messe Wien Exhibition and Congress Center, Vienna, Austria, May 7-11t, 2024 
Merknad

QC 20240515

Tilgjengelig fra: 2024-05-15 Laget: 2024-05-15 Sist oppdatert: 2024-05-16bibliografisk kontrollert
Inngår i avhandling
1. On Label Noise in Image Classification: An Aleatoric Uncertainty Perspective
Åpne denne publikasjonen i ny fane eller vindu >>On Label Noise in Image Classification: An Aleatoric Uncertainty Perspective
2024 (engelsk)Doktoravhandling, med artikler (Annet vitenskapelig)
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.

sted, utgiver, år, opplag, sider
Stockholm: KTH Royal Institute of Technology, 2024. s. xi, 68
Serie
TRITA-EECS-AVL ; 2024:45
Emneord
Label noise, aleatoric uncertainty, noisy labels, robustness, etikettbrus, osäkerhet, felmarkerade etiketter, robusthet
HSV kategori
Forskningsprogram
Datalogi
Identifikatorer
urn:nbn:se:kth:diva-346453 (URN)978-91-8040-925-4 (ISBN)
Disputas
2024-06-03, https://kth-se.zoom.us/w/61097277235, F3 (Flodis), Lindstedsvägen 26 & 28, Stockholm, 09:00 (engelsk)
Opponent
Veileder
Forskningsfinansiär
Wallenberg AI, Autonomous Systems and Software Program (WASP)
Merknad

QC 20240516

Tilgjengelig fra: 2024-05-16 Laget: 2024-05-16 Sist oppdatert: 2025-12-03bibliografisk kontrollert

Open Access i DiVA

fulltext(638 kB)623 nedlastinger
Filinformasjon
Fil FULLTEXT01.pdfFilstørrelse 638 kBChecksum SHA-512
f952c89b51235c2043d98226d40f4939ca7b532da9d8e2dff03899bfd18c51d4336f03a5b32d06b4d1da01ca5b694354aa25727098c246eefd5669bcc50e4354
Type fulltextMimetype application/pdf

Andre lenker

PaperCode

Person

Englesson, ErikAzizpour, Hossein

Søk i DiVA

Av forfatter/redaktør
Englesson, ErikAzizpour, Hossein
Av organisasjonen

Søk utenfor DiVA

GoogleGoogle Scholar
Totalt: 623 nedlastinger
Antall nedlastinger er summen av alle nedlastinger av alle fulltekster. Det kan for eksempel være tidligere versjoner som er ikke lenger tilgjengelige

urn-nbn

Altmetric

urn-nbn
Totalt: 3267 treff
RefereraExporteraLink to record
Permanent link

Direct link
Referera
Referensformat
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Annet format
Fler format
Språk
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Annet språk
Fler språk
Utmatningsformat
  • html
  • text
  • asciidoc
  • rtf