paper-with-me

홈 › Papers

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 large losses, which are critical for achieving the model's close-to-optimal generalization performance. In this paper, we propose a new framework, Late Stopping, which leverages the intrinsic robust learning ability of DNNs through a prolonged training process. Specifically, Late Stopping gradually shrinks the noisy dataset by removing high-probability mislabeled examples while retaining the majority of clean hard examples in the training set throughout the learning process. We empirically observe that mislabeled and clean examples exhibit differences in the number of epochs required for them to be consistently and correctly classified, and thus high-probability mislabeled examples can be removed. Experimental results on benchmark-simulated and real-world noisy datasets demonstrate that the proposed method outperforms state-of-the-art counterparts.

📄 PDF Abstract BibTeX arXiv:2308.13862

Code (1)

tmllab/2023_ICCV_LateStopping 공식 구현 pytorch

Tasks

Learning with noisy labels

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

Subclass-Dominant Label Noise: A Counterexample for the Success of Early Stopping

2023-09-21 · NeurIPS 2023 11

In this paper, we empirically investigate a previously overlooked and widespread type of label noise, subclass-dominant label noise (SDN). Our findings reveal that, during the early stages of training, deep neural networ…

Tackling Noisy Labels with Network Parameter Additive Decomposition

2024-03-20 · Jingyi Wang, Xiaobo Xia, Long Lan, Xinghao Wu 외

Given data with noisy labels, over-parameterized deep networks suffer overfitting mislabeled data, resulting in poor generalization. The memorization effect of deep networks shows that although the networks have the abil…

Memorization

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

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 da…

Learning with noisy labels