Related papers: Dynamic Loss For Robust Learning
Real-world data inevitably contains noisy labels, which induce the poor generalization of deep neural networks. It is known that the network typically begins to rapidly memorize false-labeled samples after a certain point of training. Thus,…
Learning and decision-making in domains with naturally high noise-to-signal ratio, such as Finance or Healthcare, is often challenging, while the stakes are very high. In this paper, we study the problem of learning and acting under a…
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…
Deep neural networks (DNNs) are powerful tools in computer vision tasks. However, in many realistic scenarios label noise is prevalent in the training images, and overfitting to these noisy labels can significantly harm the generalization…
The recent success of deep learning is mostly due to the availability of big datasets with clean annotations. However, gathering a cleanly annotated dataset is not always feasible due to practical challenges. As a result, label noise is a…
The challenge of learning with noisy labels is significant in machine learning, as it can severely degrade the performance of prediction models if not addressed properly. This paper introduces a novel framework that conceptualizes noisy…
Data augmentation plays a pivotal role in enhancing and diversifying training data. Nonetheless, consistently improving model performance in varied learning scenarios, especially those with inherent data biases, remains challenging. To…
The prediction of disease risk factors can screen vulnerable groups for effective prevention and treatment, so as to reduce their morbidity and mortality. Machine learning has a great demand for high-quality labeling information, and…
Deep neural networks are known to be annotation-hungry. Numerous efforts have been devoted to reducing the annotation cost when learning with deep networks. Two prominent directions include learning with noisy labels and semi-supervised…
Today's available datasets in the wild, e.g., from social media and open platforms, present tremendous opportunities and challenges for deep learning, as there is a significant portion of tagged images, but often with noisy, i.e. erroneous,…
Training data plays an essential role in modern applications of machine learning. However, gathering labeled training data is time-consuming. Therefore, labeling is often outsourced to less experienced users, or completely automated. This…
In open-world semi-supervised learning, a machine learning model is tasked with uncovering novel categories from unlabeled data while maintaining performance on seen categories from labeled data. The central challenge is the substantial…
Deep neural networks have incredible capacity and expressibility, and can seemingly memorize any training set. This introduces a problem when training in the presence of noisy labels, as the noisy examples cannot be distinguished from clean…
Learning from noisy labels (LNL) is a challenge that arises in many real-world scenarios where collected training data can contain incorrect or corrupted labels. Most existing solutions identify noisy labels and adopt active learning to…
Mislabeled samples are ubiquitous in real-world datasets as rule-based or expert labeling is usually based on incorrect assumptions or subject to biased opinions. Neural networks can "memorize" these mislabeled samples and, as a result,…
Existing dynamic data pruning methods often fail under noisy-label settings, as they typically rely on per-sample loss as the ranking criterion. This could mistakenly lead to preserving noisy samples due to their high loss values, resulting…
Noisy Labels are commonly present in data sets automatically collected from the internet, mislabeled by non-specialist annotators, or even specialists in a challenging task, such as in the medical field. Although deep learning models have…
It has been shown that deep neural networks are prone to overfitting on biased training data. Towards addressing this issue, meta-learning employs a meta model for correcting the training bias. Despite the promising performances, super slow…
Learning with noisy labels is one of the hottest problems in weakly-supervised learning. Based on memorization effects of deep neural networks, training on small-loss instances becomes very promising for handling noisy labels. This fosters…
Existing research on learning with noisy labels mainly focuses on synthetic label noise. Synthetic noise, though has clean structures which greatly enabled statistical analyses, often fails to model real-world noise patterns. The recent…