Details
| Original language | English |
|---|---|
| Title of host publication | Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops |
| Pages | 2295-2304 |
| Number of pages | 10 |
| Publication status | E-pub ahead of print - 1 Jun 2024 |
Abstract
<html xmlns="http://www.w3.org/1999/xhtml">
<head>
<title>Semi-supervised Learning for Multi-label Classification</title>
<meta charset="UTF-8" />
</head>
<body>
<p>
Semi-supervised learning (SSL) has achieved remarkable success for multiclass classification in recent years,
yielding a promising solution for medical image classification where labeled data is scarce but unlabeled images are accessible.
In the context of multi-label problems, however, SSL is still under-explored.
In this work, we adapt FixMatch to the multi-label scenario, specifically focusing on CheXpert,
a multi-label chest X-ray classification dataset which is imbalanced and only partially labeled.
</p>
<p>
Leveraging distribution alignment, our proposed method, ML-FixMatch+DA, achieves solid performance gains in SSL tasks
(AUC: +2.6%) and in a missing label scenario (AUC: +1.9%).
In contrast to previous work, we achieve a performance gain on CheXpert using FixMatch.
We show that in contrast to multiclass FixMatch, where distribution alignment is optional,
it is essential for multi-label FixMatch to handle class imbalance and generate reliable (positive and negative) pseudo-labels.
</p>
<p>
Our pseudo-label selection is based on a single threshold for all classes and handles imbalance with no prior knowledge on label distributions.
Our adaptation keeps the simplicity of the original multiclass FixMatch with no added hyperparameters (even for imbalanced data)
and demonstrates the feasibility of simple SSL for multi-label problems, filling a crucial gap in the literature.
</p>
</body>
</html>
Keywords
- semi supervised learning, CheXpert, multi-label classification
Cite this
- Standard
- Harvard
- Apa
- Vancouver
- BibTeX
- RIS
Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops. 2024. p. 2295-2304.
Research output: Chapter in book/report/conference proceeding › Conference contribution › Research › peer review
}
TY - GEN
T1 - Distribution-Aware Multi-Label FixMatch for Semi-Supervised Learning on CheXpert.
AU - Ihler, Sontje
AU - Kuhnke, Felix
AU - Kuhlgatz, Timo
AU - Seel, Thomas
PY - 2024/6/1
Y1 - 2024/6/1
N2 - <!DOCTYPE html>Semi-supervised Learning for Multi-label ClassificationSemi-supervised learning (SSL) has achieved remarkable success for multiclass classification in recent years,yielding a promising solution for medical image classification where labeled data is scarce but unlabeled images are accessible.In the context of multi-label problems, however, SSL is still under-explored.In this work, we adapt FixMatch to the multi-label scenario, specifically focusing on CheXpert,a multi-label chest X-ray classification dataset which is imbalanced and only partially labeled.Leveraging distribution alignment, our proposed method, ML-FixMatch+DA, achieves solid performance gains in SSL tasks(AUC: +2.6%) and in a missing label scenario (AUC: +1.9%).In contrast to previous work, we achieve a performance gain on CheXpert using FixMatch.We show that in contrast to multiclass FixMatch, where distribution alignment is optional,it is essential for multi-label FixMatch to handle class imbalance and generate reliable (positive and negative) pseudo-labels.Our pseudo-label selection is based on a single threshold for all classes and handles imbalance with no prior knowledge on label distributions.Our adaptation keeps the simplicity of the original multiclass FixMatch with no added hyperparameters (even for imbalanced data)and demonstrates the feasibility of simple SSL for multi-label problems, filling a crucial gap in the literature.
AB - <!DOCTYPE html>Semi-supervised Learning for Multi-label ClassificationSemi-supervised learning (SSL) has achieved remarkable success for multiclass classification in recent years,yielding a promising solution for medical image classification where labeled data is scarce but unlabeled images are accessible.In the context of multi-label problems, however, SSL is still under-explored.In this work, we adapt FixMatch to the multi-label scenario, specifically focusing on CheXpert,a multi-label chest X-ray classification dataset which is imbalanced and only partially labeled.Leveraging distribution alignment, our proposed method, ML-FixMatch+DA, achieves solid performance gains in SSL tasks(AUC: +2.6%) and in a missing label scenario (AUC: +1.9%).In contrast to previous work, we achieve a performance gain on CheXpert using FixMatch.We show that in contrast to multiclass FixMatch, where distribution alignment is optional,it is essential for multi-label FixMatch to handle class imbalance and generate reliable (positive and negative) pseudo-labels.Our pseudo-label selection is based on a single threshold for all classes and handles imbalance with no prior knowledge on label distributions.Our adaptation keeps the simplicity of the original multiclass FixMatch with no added hyperparameters (even for imbalanced data)and demonstrates the feasibility of simple SSL for multi-label problems, filling a crucial gap in the literature.
KW - semi supervised learning
KW - CheXpert
KW - multi-label classification
M3 - Conference contribution
SP - 2295
EP - 2304
BT - Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops
ER -