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 …

Deep networks have strong capacities of embedding data into latent representations and
finishing following tasks. However, the capacities largely come from high-quality annotated …

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 …

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

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 …

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 …

The existing weakly supervised semantic segmentation (WSSS) methods pay much
attention to generating accurate and complete class activation maps (CAMs) as pseudo …

Source-free domain adaptation (SFDA) newly emerges to transfer the relevant knowledge of
a well-trained source model to an unlabeled target domain, which is critical in various …

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 …