Due to domain shift, deep learning image classifiers perform poorly whenapplied to a domain different from the training one. For instance, a classifiertrained on chest X-ray (CXR) images from one hospital may not generalize toimages from another hospital due to variations in scanner settings or patientcharacteristics. In this paper, we introduce our CROCODILE framework, showinghow tools from causality can foster a model's robustness to domain shift viafeature disentanglement, contrastive learning losses, and the injection ofprior knowledge. This way, the model relies less on spurious correlations,learns the mechanism bringing from images to prediction better, and outperformsbaselines on out-of-distribution (OOD) data. We apply our method to multi-labellung disease classification from CXRs, utilizing over 750000 images from fourdatasets. Our bias-mitigation method improves domain generalization andfairness, broadening the applicability and reliability of deep learning modelsfor a safer medical image analysis. Find our code at:https://github.com/gianlucarloni/crocodile.

CROCODILE: Causality aids RObustness via COntrastive DIsentangled LEarning

Carloni G.;Colantonio S.
2024

Abstract

Due to domain shift, deep learning image classifiers perform poorly whenapplied to a domain different from the training one. For instance, a classifiertrained on chest X-ray (CXR) images from one hospital may not generalize toimages from another hospital due to variations in scanner settings or patientcharacteristics. In this paper, we introduce our CROCODILE framework, showinghow tools from causality can foster a model's robustness to domain shift viafeature disentanglement, contrastive learning losses, and the injection ofprior knowledge. This way, the model relies less on spurious correlations,learns the mechanism bringing from images to prediction better, and outperformsbaselines on out-of-distribution (OOD) data. We apply our method to multi-labellung disease classification from CXRs, utilizing over 750000 images from fourdatasets. Our bias-mitigation method improves domain generalization andfairness, broadening the applicability and reliability of deep learning modelsfor a safer medical image analysis. Find our code at:https://github.com/gianlucarloni/crocodile.
2024
Istituto di Scienza e Tecnologie dell'Informazione "Alessandro Faedo" - ISTI
978-3-031-73158-7
Domain shift robustness, Out-of-distribution, Causality
File in questo prodotto:
File Dimensione Formato  
2408.04949v1.pdf

accesso aperto

Tipologia: Documento in Pre-print
Licenza: Creative commons
Dimensione 2.3 MB
Formato Adobe PDF
2.3 MB Adobe PDF Visualizza/Apri
Carloni-Colantonio_LNCS-2024.pdf

solo utenti autorizzati

Descrizione: CROCODILE: Causality Aids RObustness via COntrastive DIsentangled LEarning
Tipologia: Versione Editoriale (PDF)
Licenza: NON PUBBLICO - Accesso privato/ristretto
Dimensione 1.78 MB
Formato Adobe PDF
1.78 MB Adobe PDF   Visualizza/Apri   Richiedi una copia

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/20.500.14243/498824
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus ND
  • ???jsp.display-item.citation.isi??? 0
social impact