Deep learning has achieved remarkable success in numerous domains with help from large
amounts of big data. However, the quality of data labels is a concern because of the lack of …

Data-centric AI is at the center of a fundamental shift in software engineering where machine
learning becomes the new software, powered by big data and computing infrastructure …

Self-training is a competitive approach in domain adaptive segmentation, which trains the
network with the pseudo labels on the target domain. However inevitably, the pseudo labels …

We propose a novel framework to perform classification via deep learning in the presence of
noisy annotations. When trained on noisy labels, deep neural networks have been observed …

Recently, over-parameterized deep networks, with increasingly more network parameters
than training samples, have dominated the performances of modern machine learning …

Existing studies indicate that deep neural networks (DNNs) can eventually memorize the
label noise. We observe that the memorization strength of DNNs towards each instance is …

In label-noise learning, the noise transition matrix, bridging the class posterior for noisy and
clean data, has been widely exploited to learn statistically consistent classifiers. The …

Label noise has been a practical challenge in deep learning due to the strong capability of
deep neural networks in fitting all training data. Prior literature primarily resorts to sample …

Learning with noisy labels is a common challenge in supervised learning. Existing
approaches often require practitioners to specify noise rates, ie, a set of parameters …

Noisy labels, resulting from mistakes in manual labeling or webly data collecting for
supervised learning, can cause neural networks to overfit the misleading information and …