Using Under-trained Deep Ensembles to Learn Under Extreme Label Noise
- URL: http://arxiv.org/abs/2009.11128v2
- Date: Mon, 15 Nov 2021 12:37:53 GMT
- Title: Using Under-trained Deep Ensembles to Learn Under Extreme Label Noise
- Authors: Konstantinos Nikolaidis, Thomas Plagemann, Stein Kristiansen, Vera
Goebel, Mohan Kankanhalli
- Abstract summary: We propose an effective new approach for learning under extreme label noise, based on under-trained deep ensembles.
We focus on a healthcare setting and extensively evaluate our approach on the task of sleep apnea detection.
- Score: 0.6999740786886535
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: Improper or erroneous labelling can pose a hindrance to reliable
generalization for supervised learning. This can have negative consequences,
especially for critical fields such as healthcare. We propose an effective new
approach for learning under extreme label noise, based on under-trained deep
ensembles. Each ensemble member is trained with a subset of the training data,
to acquire a general overview of the decision boundary separation, without
focusing on potentially erroneous details. The accumulated knowledge of the
ensemble is combined to form new labels, that determine a better class
separation than the original labels. A new model is trained with these labels
to generalize reliably despite the label noise. We focus on a healthcare
setting and extensively evaluate our approach on the task of sleep apnea
detection. For comparison with related work, we additionally evaluate on the
task of digit recognition. In our experiments, we observed performance
improvement in accuracy from 6.7\% up-to 49.3\% for the task of digit
classification and in kappa from 0.02 up-to 0.55 for the task of sleep apnea
detection.
Related papers
- Extracting Clean and Balanced Subset for Noisy Long-tailed Classification [66.47809135771698]
We develop a novel pseudo labeling method using class prototypes from the perspective of distribution matching.
By setting a manually-specific probability measure, we can reduce the side-effects of noisy and long-tailed data simultaneously.
Our method can extract this class-balanced subset with clean labels, which brings effective performance gains for long-tailed classification with label noise.
arXiv Detail & Related papers (2024-04-10T07:34:37Z) - Mitigating Label Noise through Data Ambiguation [9.51828574518325]
Large models with high expressive power are prone to memorizing incorrect labels, thereby harming generalization performance.
In this paper, we suggest to address the shortcomings of both methodologies by "ambiguating" the target information.
More precisely, we leverage the framework of so-called superset learning to construct set-valued targets based on a confidence threshold.
arXiv Detail & Related papers (2023-05-23T07:29:08Z) - Blind Knowledge Distillation for Robust Image Classification [19.668440671541546]
Blind Knowledge Distillation is a teacher-student approach for learning with noisy labels.
We use Otsus algorithm to estimate the tipping point from generalizing to overfitting.
We show in our experiments that Blind Knowledge Distillation detects overfitting effectively during training.
arXiv Detail & Related papers (2022-11-21T11:17:07Z) - Robust Medical Image Classification from Noisy Labeled Data with Global
and Local Representation Guided Co-training [73.60883490436956]
We propose a novel collaborative training paradigm with global and local representation learning for robust medical image classification.
We employ the self-ensemble model with a noisy label filter to efficiently select the clean and noisy samples.
We also design a novel global and local representation learning scheme to implicitly regularize the networks to utilize noisy samples.
arXiv Detail & Related papers (2022-05-10T07:50:08Z) - Two Wrongs Don't Make a Right: Combating Confirmation Bias in Learning
with Label Noise [6.303101074386922]
Robust Label Refurbishment (Robust LR) is a new hybrid method that integrates pseudo-labeling and confidence estimation techniques to refurbish noisy labels.
We show that our method successfully alleviates the damage of both label noise and confirmation bias.
For example, Robust LR achieves up to 4.5% absolute top-1 accuracy improvement over the previous best on the real-world noisy dataset WebVision.
arXiv Detail & Related papers (2021-12-06T12:10:17Z) - Combating Noise: Semi-supervised Learning by Region Uncertainty
Quantification [55.23467274564417]
Current methods are easily distracted by noisy regions generated by pseudo labels.
We propose noise-resistant semi-supervised learning by quantifying the region uncertainty.
Experiments on both PASCAL VOC and MS COCO demonstrate the extraordinary performance of our method.
arXiv Detail & Related papers (2021-11-01T13:23:42Z) - Label Noise in Adversarial Training: A Novel Perspective to Study Robust
Overfitting [45.58217741522973]
We show that label noise exists in adversarial training.
Such label noise is due to the mismatch between the true label distribution of adversarial examples and the label inherited from clean examples.
We propose a method to automatically calibrate the label to address the label noise and robust overfitting.
arXiv Detail & Related papers (2021-10-07T01:15:06Z) - Co-Correcting: Noise-tolerant Medical Image Classification via mutual
Label Correction [5.994566233473544]
This paper proposes a noise-tolerant medical image classification framework named Co-Correcting.
It significantly improves classification accuracy and obtains more accurate labels through dual-network mutual learning, label probability estimation, and curriculum label correcting.
Experiments show that Co-Correcting achieves the best accuracy and generalization under different noise ratios in various tasks.
arXiv Detail & Related papers (2021-09-11T02:09:52Z) - Robust Long-Tailed Learning under Label Noise [50.00837134041317]
This work investigates the label noise problem under long-tailed label distribution.
We propose a robust framework,algo, that realizes noise detection for long-tailed learning.
Our framework can naturally leverage semi-supervised learning algorithms to further improve the generalisation.
arXiv Detail & Related papers (2021-08-26T03:45:00Z) - Disentangling Sampling and Labeling Bias for Learning in Large-Output
Spaces [64.23172847182109]
We show that different negative sampling schemes implicitly trade-off performance on dominant versus rare labels.
We provide a unified means to explicitly tackle both sampling bias, arising from working with a subset of all labels, and labeling bias, which is inherent to the data due to label imbalance.
arXiv Detail & Related papers (2021-05-12T15:40:13Z) - Improving Medical Image Classification with Label Noise Using
Dual-uncertainty Estimation [72.0276067144762]
We discuss and define the two common types of label noise in medical images.
We propose an uncertainty estimation-based framework to handle these two label noise amid the medical image classification task.
arXiv Detail & Related papers (2021-02-28T14:56:45Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.