Related papers: To Aggregate or Not? Learning with Separate Noisy …

Learning segmentation from noisy labels is an important task for medical image analysis due to the difficulty in acquiring highquality annotations. Most existing methods neglect the pixel correlation and structural prior in segmentation,…

NLP models often rely on human-labeled data for training and evaluation. Many approaches crowdsource this data from a large number of annotators with varying skills, backgrounds, and motivations, resulting in conflicting annotations. These…

Algorithms which minimize the averaged loss have been widely designed for dealing with noisy labels. Intuitively, when there is a finite training sample, penalizing the variance of losses will improve the stability and generalization of the…

Deep Learning systems have shown tremendous accuracy in image classification, at the cost of big image datasets. Collecting such amounts of data can lead to labelling errors in the training set. Indexing multimedia content for retrieval,…

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…

As an open research topic in the field of deep learning, learning with noisy labels has attracted much attention and grown rapidly over the past ten years. Learning with label noise is crucial for driver distraction behavior recognition, as…

Deep neural networks are prone to overfitting noisy labels, resulting in poor generalization performance. To overcome this problem, we present a simple and effective method self-ensemble label correction (SELC) to progressively correct…

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…

The label noise transition matrix, characterizing the probabilities of a training instance being wrongly annotated, is crucial to designing popular solutions to learning with noisy labels. Existing works heavily rely on finding "anchor…

Bipartite ranking is a fundamental supervised learning problem, with the goal of learning a ranking over instances with maximal Area Under the ROC Curve (AUC) against a single binary target label. However, one may often observe multiple…

Labels noise refers to errors in training labels caused by cheap data annotation methods, such as web scraping or crowd-sourcing, which can be detrimental to the performance of supervised classifiers. Several methods have been proposed to…

This paper aims to provide understandings for the effect of an over-parameterized model, e.g. a deep neural network, memorizing instance-dependent noisy labels. We first quantify the harms caused by memorizing noisy instances, and show the…

A similarity label indicates whether two instances belong to the same class while a class label shows the class of the instance. Without class labels, a multi-class classifier could be learned from similarity-labeled pairwise data by meta…

In noisy label learning, estimating noisy class posteriors plays a fundamental role for developing consistent classifiers, as it forms the basis for estimating clean class posteriors and the transition matrix. Existing methods typically…

Collecting large-scale data with clean labels for supervised training of neural networks is practically challenging. Although noisy labels are usually cheap to acquire, existing methods suffer a lot from label noise. This paper targets at…

Due to the privacy protection or the difficulty of data collection, we cannot observe individual outputs for each instance, but we can observe aggregated outputs that are summed over multiple instances in a set in some real-world…

High quality labeled datasets have allowed deep learning to achieve impressive results on many sound analysis tasks. Yet, it is labor-intensive to accurately annotate large amount of audio data, and the dataset may contain noisy labels in…

In Multi-Label Learning (MLL), it is extremely challenging to accurately annotate every appearing object due to expensive costs and limited knowledge. When facing such a challenge, a more practical and cheaper alternative should be Single…

In low-resource settings, the performance of supervised labeling models can be improved with automatically annotated or distantly supervised data, which is cheap to create but often noisy. Previous works have shown that significant…

Learning with noisy labels has aroused much research interest since data annotations, especially for large-scale datasets, may be inevitably imperfect. Recent approaches resort to a semi-supervised learning problem by dividing training…