Related papers: Learning from Multiple Annotator Noisy Labels via …
Solving complex classification tasks using deep neural networks typically requires large amounts of annotated data. However, corresponding class labels are noisy when provided by error-prone annotators, e.g., crowdworkers. Training standard…
Deep neural network models are robust to a limited amount of label noise, but their ability to memorise noisy labels in high noise rate problems is still an open issue. The most competitive noisy-label learning algorithms rely on a 2-stage…
Recent studies in deep learning have shown significant progress in named entity recognition (NER). Most existing works assume clean data annotation, yet a fundamental challenge in real-world scenarios is the large amount of noise from a…
Deep learning with noisy labels is an interesting challenge in weakly supervised learning. Despite their significant learning capacity, CNNs have a tendency to overfit in the presence of samples with noisy labels. Alleviating this issue,…
Deep learning methods have achieved promising performance in many areas, but they are still struggling with noisy-labeled images during the training process. Considering that the annotation quality indispensably relies on great expertise,…
In this paper, we consider a novel machine learning problem, that is, learning a classifier from noisy label distributions. In this problem, each instance with a feature vector belongs to at least one group. Then, instead of the true label…
One-hot labels do not represent soft decision boundaries among concepts, and hence, models trained on them are prone to overfitting. Using soft labels as targets provide regularization, but different soft labels might be optimal at…
Computer vision systems recently made a big leap thanks to deep neural networks. However, these systems require correctly labeled large datasets in order to be trained properly, which is very difficult to obtain for medical applications.…
There has been much interest in recent years in learning good classifiers from data with noisy labels. Most work on learning from noisy labels has focused on standard loss-based performance measures. However, many machine learning problems…
For multi-class classification under class-conditional label noise, we prove that the accuracy metric itself can be robust. We concretize this finding's inspiration in two essential aspects: training and validation, with which we address…
Numerous researches have proved that deep neural networks (DNNs) can fit everything in the end even given data with noisy labels, and result in poor generalization performance. However, recent studies suggest that DNNs tend to gradually…
In real-world data labeling applications, annotators often provide imperfect labels. It is thus common to employ multiple annotators to label data with some overlap between their examples. We study active learning in such settings, aiming…
For high-resource languages like English, text classification is a well-studied task. The performance of modern NLP models easily achieves an accuracy of more than 90% in many standard datasets for text classification in English (Xie et…
Multi-label classification (MLC) is a generalization of standard classification where multiple labels may be assigned to a given sample. In the real world, it is more common to deal with noisy datasets than clean datasets, given how modern…
Deep neural networks (DNNs) have achieved great success in a wide variety of medical image analysis tasks. However, these achievements indispensably rely on the accurately-annotated datasets. If with the noisy-labeled images, the training…
Deep learning faces a formidable challenge when handling noisy labels, as models tend to overfit samples affected by label noise. This challenge is further compounded by the presence of instance-dependent noise (IDN), a realistic form of…
Noisy multi-label learning has garnered increasing attention due to the challenges posed by collecting large-scale accurate labels, making noisy labels a more practical alternative. Motivated by noisy multi-class learning, the introduction…
Noisy labels damage the performance of deep networks. For robust learning, a prominent two-stage pipeline alternates between eliminating possible incorrect labels and semi-supervised training. However, discarding part of noisy labels could…
The success of current deep saliency detection methods heavily depends on the availability of large-scale supervision in the form of per-pixel labeling. Such supervision, while labor-intensive and not always possible, tends to hinder the…
Label noise is a critical factor that degrades the generalization performance of deep neural networks, thus leading to severe issues in real-world problems. Existing studies have employed strategies based on either loss or uncertainty to…