Related papers: Tripartite: Tackle Noisy Labels by a More Precise …

Data pruning, which aims to downsize a large training set into a small informative subset, is crucial for reducing the enormous computational costs of modern deep learning. Though large-scale data collections invariably contain annotation…

Current methods focusing on medical image segmentation suffer from incorrect annotations, which is known as the noisy label issue. Most medical image segmentation with noisy labels methods utilize either noise transition matrix,…

The proliferation of extensive neural network architectures, particularly deep learning models, presents a challenge in terms of resource-intensive training. GPU memory constraints have become a notable bottleneck in training such sizable…

Imperfections in data annotation, known as label noise, are detrimental to the training of machine learning models and have an often-overlooked confounding effect on the assessment of model performance. Nevertheless, employing experts to…

Learning deep neural network (DNN) classifier with noisy labels is a challenging task because the DNN can easily over-fit on these noisy labels due to its high capability. In this paper, we present a very simple but effective training…

Deep neural network models have demonstrated their effectiveness in classifying multi-label data from various domains. Typically, they employ a training mode that combines mini-batches with optimizers, where each sample is randomly selected…

The rawly collected training data often comes with separate noisy labels collected from multiple imperfect annotators (e.g., via crowdsourcing). A typical way of using these separate labels is to first aggregate them into one and apply…

Label noise is one of the key factors that lead to the poor generalization of deep learning models. Existing label-noise learning methods usually assume that the ground-truth classes of the training data are balanced. However, the…

Federated learning (FL) aims to learn joint knowledge from a large scale of decentralized devices with labeled data in a privacy-preserving manner. However, since high-quality labeled data require expensive human intelligence and efforts,…

The problem of open-set noisy labels denotes that part of training data have a different label space that does not contain the true class. Lots of approaches, e.g., loss correction and label correction, cannot handle such open-set noisy…

In the field of medical image analysis, deep learning models have demonstrated remarkable success in enhancing diagnostic accuracy and efficiency. However, the reliability of these models is heavily dependent on the quality of training…

Training a deep neural network heavily relies on a large amount of training data with accurate annotations. To alleviate this problem, various methods have been proposed to annotate the data automatically. However, automatically generating…

Deep neural networks (DNNs) offer a means of addressing the challenging task of clustering high-dimensional data. DNNs can extract useful features, and so produce a lower dimensional representation, which is more amenable to clustering…

Distant and weak supervision allow to obtain large amounts of labeled training data quickly and cheaply, but these automatic annotations tend to contain a high amount of errors. A popular technique to overcome the negative effects of these…

Learning with noisy labels (LNL) aims at designing strategies to improve model performance and generalization by mitigating the effects of model overfitting to noisy labels. The key success of LNL lies in identifying as many clean samples…

Collecting labeled data to train deep neural networks is costly and even impractical for many tasks. Thus, research effort has been focused in automatically curated datasets or unsupervised and weakly supervised learning. The common problem…

The performance of a model trained with noisy labels is often improved by simply \textit{retraining} the model with its \textit{own predicted hard labels} (i.e., 1/0 labels). Yet, a detailed theoretical characterization of this phenomenon…

Several works in computer vision have demonstrated the effectiveness of active learning for adapting the recognition model when new unlabeled data becomes available. Most of these works consider that labels obtained from the annotator are…

Deep neural networks (DNN) have been successfully applied to music classification including music tagging. However, there are several open questions regarding the training, evaluation, and analysis of DNNs. In this article, we investigate…

Large-scale datasets have driven the rapid development of deep neural networks for visual recognition. However, annotating a massive dataset is expensive and time-consuming. Web images and their labels are, in comparison, much easier to…