The memorization effect of deep neural network (DNN) plays a pivotal role in many state-of-
the-art label-noise learning methods. To exploit this property, the early stopping trick, which …

In this work, we study hallucinations in Neural Machine Translation (NMT), which lie at an
extreme end on the spectrum of NMT pathologies. Firstly, we connect the phenomenon of …

Cross-modal matching, which aims to establish the correspondence between two different
modalities, is fundamental to a variety of tasks such as cross-modal retrieval and vision-and …

In learning with noisy labels, the sample selection approach is very popular, which regards
small-loss data as correctly labeled during training. However, losses are generated on-the …

The presence of label noise often misleads the training of deep neural networks. Departing
from the recent literature which largely assumes the label noise rate is only determined by …

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 …

The existence of noisy data is prevalent in both the training and testing phases of machine
learning systems, which inevitably leads to the degradation of model performance. There …

Modern deep neural networks (DNNs) become frail when the datasets contain noisy
(incorrect) class labels. Robust techniques in the presence of noisy labels can be …

Learning with noisy labels is a practically challenging problem in weakly supervised
learning. In the existing literature, open-set noises are always considered to be poisonous …

The recent breakthrough achieved by contrastive learning accelerates the pace for
deploying unsupervised training on real-world data applications. However, unlabeled data …