Enregistré dans:
Détails bibliographiques
Auteurs principaux: Dedieu, Lucas, Nerrienet, Nicolas, Nivaggioli, Adrien, Simmat, Clara, Clavel, Marceau, Gauthier, Arnaud, Sockeel, Stéphane, Peyret, Rémy
Format: Preprint
Publié: 2024
Sujets:
Accès en ligne:https://arxiv.org/abs/2404.07605
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866929310931091456
author Dedieu, Lucas
Nerrienet, Nicolas
Nivaggioli, Adrien
Simmat, Clara
Clavel, Marceau
Gauthier, Arnaud
Sockeel, Stéphane
Peyret, Rémy
author_facet Dedieu, Lucas
Nerrienet, Nicolas
Nivaggioli, Adrien
Simmat, Clara
Clavel, Marceau
Gauthier, Arnaud
Sockeel, Stéphane
Peyret, Rémy
contents Recent advancements in deep learning have proven highly effective in medical image classification, notably within histopathology. However, noisy labels represent a critical challenge in histopathology image classification, where accurate annotations are vital for training robust deep learning models. Indeed, deep neural networks can easily overfit label noise, leading to severe degradations in model performance. While numerous public pathology foundation models have emerged recently, none have evaluated their resilience to label noise. Through thorough empirical analyses across multiple datasets, we exhibit the label noise resilience property of embeddings extracted from foundation models trained in a self-supervised contrastive manner. We demonstrate that training with such embeddings substantially enhances label noise robustness when compared to non-contrastive-based ones as well as commonly used noise-resilient methods. Our results unequivocally underline the superiority of contrastive learning in effectively mitigating the label noise challenge. Code is publicly available at https://github.com/LucasDedieu/NoiseResilientHistopathology.
format Preprint
id arxiv_https___arxiv_org_abs_2404_07605
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Contrastive-Based Deep Embeddings for Label Noise-Resilient Histopathology Image Classification
Dedieu, Lucas
Nerrienet, Nicolas
Nivaggioli, Adrien
Simmat, Clara
Clavel, Marceau
Gauthier, Arnaud
Sockeel, Stéphane
Peyret, Rémy
Computer Vision and Pattern Recognition
Artificial Intelligence
Recent advancements in deep learning have proven highly effective in medical image classification, notably within histopathology. However, noisy labels represent a critical challenge in histopathology image classification, where accurate annotations are vital for training robust deep learning models. Indeed, deep neural networks can easily overfit label noise, leading to severe degradations in model performance. While numerous public pathology foundation models have emerged recently, none have evaluated their resilience to label noise. Through thorough empirical analyses across multiple datasets, we exhibit the label noise resilience property of embeddings extracted from foundation models trained in a self-supervised contrastive manner. We demonstrate that training with such embeddings substantially enhances label noise robustness when compared to non-contrastive-based ones as well as commonly used noise-resilient methods. Our results unequivocally underline the superiority of contrastive learning in effectively mitigating the label noise challenge. Code is publicly available at https://github.com/LucasDedieu/NoiseResilientHistopathology.
title Contrastive-Based Deep Embeddings for Label Noise-Resilient Histopathology Image Classification
topic Computer Vision and Pattern Recognition
Artificial Intelligence
url https://arxiv.org/abs/2404.07605