The memorization effects of deep networks show that they will first memorize training data
with clean labels and then those with noisy labels. The early stopping method therefore can …

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 …

Human-annotated labels are often prone to noise, and the presence of such noise will
degrade the performance of the resulting deep neural network (DNN) models. Much of the …

The sample selection approach is popular in learning with noisy labels. The state-of-the-art
methods train two deep networks simultaneously for sample selection, which aims to employ …

In label-noise learning, estimating the transition matrix has attracted more and more
attention as the matrix plays an important role in building statistically consistent classifiers …

Classical machine learning implicitly assumes that labels of the training data are sampled
from a clean distribution, which can be too restrictive for real-world scenarios. However …

In label-noise learning, the transition matrix plays a key role in building statistically
consistent classifiers. Existing consistent estimators for the transition matrix have been …

Open-vocabulary instance segmentation aims at segmenting novel classes without mask
annotations. It is an important step toward reducing laborious human supervision. Most …

Multi-label classification aims to learn classification models from instances associated with
multiple labels. It is pivotal to learn and utilize the label dependence among multiple labels …