paper-with-me

홈 › Papers

Early Stopping Against Label Noise Without Validation Data

2025-02-11 · Suqin Yuan, Lei Feng, Tongliang Liu

Early stopping methods in deep learning face the challenge of balancing the volume of training and validation data, especially in the presence of label noise. Concretely, sparing more data for validation from training data would limit the performance of the learned model, yet insufficient validation data could result in a sub-optimal selection of the desired model. In this paper, we propose a novel early stopping method called Label Wave, which does not require validation data for selecting the desired model in the presence of label noise. It works by tracking the changes in the model's predictions on the training set during the training process, aiming to halt training before the model unduly fits mislabeled data. This method is empirically supported by our observation that minimum fluctuations in predictions typically occur at the training epoch before the model excessively fits mislabeled data. Through extensive experiments, we show both the effectiveness of the Label Wave method across various settings and its capability to enhance the performance of existing methods for learning with noisy labels.

📄 PDF Abstract BibTeX arXiv:2502.07551

Code (1)

tmllab/2024_ICLR_LabelWave 공식 구현 pytorch

Tasks

Learning with noisy labels

Methods 이 논문이 사용한 방법론

Early Stopping Early Stopping is a regularization technique for deep neural networks that stops training when parameter updates no longer begin to yield improves on a validation set. In…
SET Dynamic Sparse Training method where weight mask is updated randomly periodically

Similar Papers 제목 키워드 기반

Prestopping: How Does Early Stopping Help Generalization Against Label Noise?

2019-09-25 · Hwanjun Song, Minseok Kim, Dongmin Park, Jae-Gil Lee

Noisy labels are very common in real-world training data, which lead to poor generalization on test data because of overfitting to the noisy labels. In this paper, we claim that such overfitting can be avoided by "early …

How does Early Stopping Help Generalization against Label Noise?

2019-11-19 · Hwanjun Song, Minseok Kim, Dongmin Park, Jae-Gil Lee

Noisy labels are very common in real-world training data, which lead to poor generalization on test data because of overfitting to the noisy labels. In this paper, we claim that such overfitting can be avoided by "early …

Noisy Early Stopping for Noisy Labels

2024-09-10 · William Toner, Amos Storkey

Training neural network classifiers on datasets contaminated with noisy labels significantly increases the risk of overfitting. Thus, effectively implementing Early Stopping in noisy label environments is crucial. Under …

PADDLES: Phase-Amplitude Spectrum Disentangled Early Stopping for Learning with Noisy Labels

2022-12-07 · ICCV 2023 1 · Huaxi Huang, Hui Kang, Sheng Liu, Olivier Salvado 외

Convolutional Neural Networks (CNNs) have demonstrated superiority in learning patterns, but are sensitive to label noises and may overfit noisy labels during training. The early stopping strategy averts updating CNNs du…

Learning with noisy labels

Understanding and Improving Early Stopping for Learning with Noisy Labels

2021-06-30 · NeurIPS 2021 12 · Yingbin Bai, Erkun Yang, Bo Han, Yanhua Yang 외

The memorization effect of deep neural network (DNN) plays a pivotal role in many state-of-the-art label-noise learning methods. To exploit this property, the early stopping trick, which stops the optimization at the ear…

image-classificationImage ClassificationLearning with noisy labelsMemorization