The challenge of addressing mixed closed-set and open-set label noise in
medical image classification remains largely unexplored. Unlike natural image
classification where there is a common practice of segregation and separate
processing of closed-set and open-set noisy samples from clean ones, medical
image classification faces difficulties due to high inter-class similarity
which complicates the identification of open-set noisy samples. Moreover,
prevailing methods do not leverage the full potential of open-set noisy samples
for label noise mitigation, often leading to their exclusion or application of
uniform soft labels. To address these issues, we propose an Extended
Noise-robust Contrastive and Open-set Feature Augmentation (ENCOFA) framework.
ENCOFA includes the Extended Noise-robust Supervised Contrastive (ENSC) Loss,
which aids in distinguishing features across classes. The ENSC loss regards
open-set noisy samples as an extended class and mitigates label noise by
weighting contrastive pairs with label reliability. Furthermore, we develop an
Open-set Feature Augmentation (OSFeatAug) module that enriches the features of
open-set samples, utilizing the model's extra capacity to prevent overfitting
to noisy data. We conducted experiments on a synthetic noisy dataset and a
real-world noisy dataset. Our results indicate the superiority of ENCOFA and
the effectiveness of leveraging the open-set noisy samples to combat label
noise.

在医学图像分类方面，为解决闭集和开放集标签噪音的问题，我们提出了一个扩展噪音鲁棒对比和开放集特征增强（ENCOFA）框架，包括扩展噪音鲁棒有监督对比（ENSC）损失和开放集特征增强（OSFeatAug）模块，针对开放集噪音样本的识别和特征提取问题进行改进，实验结果表明 ENCOFA 在噪音标签处理方面优于传统方法，并有效地利用开放集噪音样本对抗标签噪音。

释放开放集嘈杂样本潜力：针对医学图像分类的标签噪声

Unleashing the Potential of Open-set Noisy Samples Against Label Noise  for Medical Image Classification

Adversarial training is an important topic in robust deep learning, but the
community lacks attention to its practical usage. In this paper, we aim to
resolve a real-world application challenge, i.e., training a model on an
imbalanced and noisy dataset to achieve high clean accuracy and robustness,
with our proposed Omnipotent Adversarial Training (OAT). Our strategy consists
of two innovative methodologies to address the label noise and data imbalance
in the training set. We first introduce an oracle into the adversarial training
process to help the model learn a correct data-label conditional distribution.
This carefully-designed oracle can provide correct label annotations for
adversarial training. We further propose logits adjustment adversarial training
to overcome the data imbalance challenge, which can help the model learn a
Bayes-optimal distribution. Our comprehensive evaluation results show that OAT
outperforms other baselines by more than 20% clean accuracy improvement and 10%
robust accuracy improvement under the complex combinations of data imbalance
and label noise scenarios. The code can be found in
this https URL

本研究提出了全能对抗训练（OAT）方法来解决训练集中不平衡数据和有噪声的数据集，其策略包括两种创新方法：引入 Oracle 来帮助模型学习正确的数据标签条件分布，并提出 logits 调整对抗训练来克服数据不平衡的挑战。全面的评估结果表明，OAT 在数据不平衡和标签噪声的复杂组合情况下比其他基线模型具有 20％以上的清洁准确率提高和 10％的健壮性提高。