paper-with-me

홈 › Papers

Robustness and Reliability When Training With Noisy Labels

2021-10-07 · Amanda Olmin, Fredrik Lindsten

Labelling of data for supervised learning can be costly and time-consuming and the risk of incorporating label noise in large data sets is imminent. When training a flexible discriminative model using a strictly proper loss, such noise will inevitably shift the solution towards the conditional distribution over noisy labels. Nevertheless, while deep neural networks have proven capable of fitting random labels, regularisation and the use of robust loss functions empirically mitigate the effects of label noise. However, such observations concern robustness in accuracy, which is insufficient if reliable uncertainty quantification is critical. We demonstrate this by analysing the properties of the conditional distribution over noisy labels for an input-dependent noise model. In addition, we evaluate the set of robust loss functions characterised by noise-insensitive, asymptotic risk minimisers. We find that strictly proper and robust loss functions both offer asymptotic robustness in accuracy, but neither guarantee that the final model is calibrated. Moreover, even with robust loss functions, overfitting is an issue in practice. With these results, we aim to explain observed robustness of common training practices, such as early stopping, to label noise. In addition, we aim to encourage the development of new noise-robust algorithms that not only preserve accuracy but that also ensure reliability.

📄 PDF Abstract BibTeX arXiv:2110.03321

Code (0)

등록된 구현이 없습니다.

Tasks

Uncertainty Quantification

Similar Papers 제목 키워드 기반

Pathological Image Segmentation with Noisy Labels

2021-03-20 · Li Xiao, Yinhao Li, Luxi Qv, Xinxia Tian 외

Segmentation of pathological images is essential for accurate disease diagnosis. The quality of manual labels plays a critical role in segmentation accuracy; yet, in practice, the labels between pathologists could be inc…

Image SegmentationSegmentationSemantic Segmentation

On the Robustness of Monte Carlo Dropout Trained with Noisy Labels

2021-03-22 · Purvi Goel, Li Chen

The memorization effect of deep learning hinders its performance to effectively generalize on test set when learning with noisy labels. Prior study has discovered that epistemic uncertainty techniques are robust when tra…

Learning with noisy labelsMemorization

How Does a Neural Network's Architecture Impact Its Robustness to Noisy Labels?

2020-12-23 · NeurIPS 2021 12 · Jingling Li, Mozhi Zhang, Keyulu Xu, John P. Dickerson 외

Noisy labels are inevitable in large real-world datasets. In this work, we explore an area understudied by previous works -- how the network's architecture impacts its robustness to noisy labels. We provide a formal fram…

Image ClassificationLearning with noisy labels

Reliable Active Learning from Unreliable Labels via Neural Collapse Geometry

2025-10-10 · Atharv Goel, Sharat Agarwal, Saket Anand, Chetan Arora arxiv

Active Learning (AL) promises to reduce annotation cost by prioritizing informative samples, yet its reliability is undermined when labels are noisy or when the data distribution shifts. In practice, annotators make mist…

Active Learning

Calibrating Pre-trained Language Classifiers on LLM-generated Noisy Labels via Iterative Refinement

2025-05-26 · Liqin Ye, Agam Shah, Chao Zhang, Sudheer Chava

The traditional process of creating labeled datasets is labor-intensive and expensive. Recent breakthroughs in open-source large language models (LLMs) have opened up a new avenue in generating labeled datasets automatic…

Benchmarking