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 …

Abstract Weakly-supervised Temporal Action Localization (WTAL) attempts to localize the
actions in untrimmed videos using only video-level supervision. Most recent works approach …

Machine learning models deployed in the wild naturally encounter unlabeled samples from
both known and novel classes. Challenges arise in learning from both the labeled and …

In this paper, we study a novel and widely existing problem in graph matching (GM), namely,
Bi-level Noisy Correspondence (BNC), which refers to node-level noisy correspondence …

Learning with noisy labels (LNL) is one of the most important and challenging problems in
weakly-supervised learning. Recent advances adopt the sample selection strategy to …

Sample selection is a prevalent method in learning with noisy labels, where small-loss data
are typically considered as correctly labeled data. However, this method may not effectively …

Abstract Domain adaptive semantic segmentation aims to adapt a model trained on labeled
source domain to the unlabeled target domain. Self-training shows competitive potential in …

The ability to train deep neural networks under label noise is appealing, as imperfectly
annotated data are relatively cheaper to obtain. State-of-the-art approaches are based on …

Learning with noisy labels (LNL) poses a significant challenge in training a well-generalized
model while avoiding overfitting to corrupted labels. Recent advances have achieved …

There has been significant attention devoted to the effectiveness of various domains, such
as semi-supervised learning, contrastive learning, and meta-learning, in enhancing the …