paper-with-me

홈 › Papers

Calibration improves detection of mislabeled examples

2025-11-04 · Ilies Chibane, Thomas George, Pierre Nodet, Vincent Lemaire arxiv

Mislabeled data is a pervasive issue that undermines the performance of machine learning systems in real-world applications. An effective approach to mitigate this problem is to detect mislabeled instances and subject them to special treatment, such as filtering or relabeling. Automatic mislabeling detection methods typically rely on training a base machine learning model and then probing it for each instance to obtain a trust score that each provided label is genuine or incorrect. The properties of this base model are thus of paramount importance. In this paper, we investigate the impact of calibrating this model. Our empirical results show that using calibration methods improves the accuracy and robustness of mislabeled instance detection, providing a practical and effective solution for industrial applications.

📄 PDF Abstract BibTeX arXiv:2511.02738

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Enhancing Sample Selection Against Label Noise by Cutting Mislabeled Easy Examples

2025-02-12 · Suqin Yuan, Lei Feng, Bo Han, Tongliang Liu

Sample selection is a prevalent approach in learning with noisy labels, aiming to identify confident samples for training. Although existing sample selection methods have achieved decent results by reducing the noise rat…

Learning with noisy labels

Mislabeled examples detection viewed as probing machine learning models: concepts, survey and extensive benchmark

2024-10-21 · Thomas George, Pierre Nodet, Alexis Bondu, Vincent Lemaire

Mislabeled examples are ubiquitous in real-world machine learning datasets, advocating the development of techniques for automatic detection. We show that most mislabeled detection methods can be viewed as probing traine…

Better Generalization with On-the-fly Dataset Denoising

2019-05-01 · ICLR 2019 5 · Jiaming Song, Tengyu Ma, Michael Auli, Yann Dauphin

Memorization in over-parameterized neural networks can severely hurt generalization in the presence of mislabeled examples. However, mislabeled examples are to hard avoid in extremely large datasets. We address this prob…

DenoisingMemorization

Late Stopping: Avoiding Confidently Learning from Mislabeled Examples

2023-08-26 · ICCV 2023 1 · Suqin Yuan, Lei Feng, Tongliang Liu

Sample selection is a prevalent method in learning with noisy labels, where small-loss data are typically considered as correctly labeled data. However, this method may not effectively identify clean hard examples with l…

Learning with noisy labels

Characterizing Datapoints via Second-Split Forgetting

2022-10-26 · Pratyush Maini, Saurabh Garg, Zachary C. Lipton, J. Zico Kolter

Researchers investigating example hardness have increasingly focused on the dynamics by which neural networks learn and forget examples throughout training. Popular metrics derived from these dynamics include (i) the epo…