Related papers: Dynamic Loss For Robust Learning
A recently-proposed technique called self-adaptive training augments modern neural networks by allowing them to adjust training labels on the fly, to avoid overfitting to samples that may be mislabeled or otherwise non-representative. By…
The real-world data is often susceptible to label noise, which might constrict the effectiveness of the existing state of the art algorithms for ordinal regression. Existing works on ordinal regression do not take label noise into account.…
Learning against label noise is a vital topic to guarantee a reliable performance for deep neural networks. Recent research usually refers to dynamic noise modeling with model output probabilities and loss values, and then separates clean…
Manual labelling of training examples is common practice in supervised learning. When the labelling task is of non-trivial difficulty, the supplied labels may not be equal to the ground-truth labels, and label noise is introduced into the…
Label noise is ubiquitous in various machine learning scenarios such as self-labeling with model predictions and erroneous data annotation. Many existing approaches are based on heuristics such as sample losses, which might not be flexible…
This paper provides theoretical insights into high-dimensional binary classification with class-conditional noisy labels. Specifically, we study the behavior of a linear classifier with a label noisiness aware loss function, when both the…
Instance-dependent label noise is realistic but rather challenging, where the label-corruption process depends on instances directly. It causes a severe distribution shift between the distributions of training and test data, which impairs…
Semantic noise in image classification datasets, where visually similar categories are frequently mislabeled, poses a significant challenge to conventional supervised learning approaches. In this paper, we explore the potential of using…
In learning with noisy labels, the sample selection approach is very popular, which regards small-loss data as correctly labeled during training. However, losses are generated on-the-fly based on the model being trained with noisy labels,…
Labeled data is a fundamental component in training supervised deep learning models for computer vision tasks. However, the labeling process, especially for ordinal image classification where class boundaries are often ambiguous, is prone…
In many applications, training machine learning models involves using large amounts of human-annotated data. Obtaining precise labels for the data is expensive. Instead, training with weak supervision provides a low-cost alternative. We…
In many domains, collecting sufficient labeled training data for supervised machine learning requires easily accessible but noisy sources, such as crowdsourcing services or tagged Web data. Noisy labels occur frequently in data sets…
A recurring focus of the deep learning community is towards reducing the labeling effort. Data gathering and annotation using a search engine is a simple alternative to generating a fully human-annotated and human-gathered dataset. Although…
There is a growing need for models that are interpretable and have reduced energy and computational cost (e.g., in health care analytics and federated learning). Examples of algorithms to train such models include logistic regression and…
Deep neural networks trained with standard cross-entropy loss memorize noisy labels, which degrades their performance. Most research to mitigate this memorization proposes new robust classification loss functions. Conversely, we propose a…
In recent years, deep neural networks (DNNs) have gained remarkable achievement in computer vision tasks, and the success of DNNs often depends greatly on the richness of data. However, the acquisition process of data and high-quality…
Label noise has been broadly observed in real-world datasets. To mitigate the negative impact of overfitting to label noise for deep models, effective strategies (\textit{e.g.}, re-weighting, or loss rectification) have been broadly applied…
There is an emerging trend to leverage noisy image datasets in many visual recognition tasks. However, the label noise among the datasets severely degenerates the \mbox{performance of deep} learning approaches. Recently, one mainstream is…
Deep neural networks have been shown to easily overfit to biased training data with label noise or class imbalance. Meta-learning algorithms are commonly designed to alleviate this issue in the form of sample reweighting, by learning a meta…
Deep learning with noisy labels is practically challenging, as the capacity of deep models is so high that they can totally memorize these noisy labels sooner or later during training. Nonetheless, recent studies on the memorization effects…