454 citations · 3.1k across the 117 of their papers we have counts for
17 papers · 1 filter
SemiNLL: A Framework of Noisy-Label Learning by Semi-Supervised Learning
Zhuowei Wang, Jing Jiang, Bo Han +4
Deep learning with noisy labels is a challenging task. Recent prominent methods that build on a specific sample selection (SS) strategy and a specific semi-supervised learning (SSL…
A Survey of Label-noise Representation Learning: Past, Present and Future
Bo Han, Quanming Yao, Tongliang Liu +4
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…
Maximum Mean Discrepancy Test is Aware of Adversarial Attacks
Ruize Gao, Feng Liu, Jingfeng Zhang +4
The maximum mean discrepancy (MMD) test could in principle detect any distributional discrepancy between two datasets. However, it has been shown that the MMD test is unaware of ad…
Pointwise Binary Classification with Pairwise Confidence Comparisons
Lei Feng, Senlin Shu, Nan Lu +5
To alleviate the data requirement for training effective binary classifiers in binary classification, many weakly supervised learning settings have been proposed. Among them, some…
Geometry-aware Instance-reweighted Adversarial Training
Jingfeng Zhang, Jianing Zhu, Gang Niu +3
In adversarial machine learning, there was a common belief that robustness and accuracy hurt each other. The belief was challenged by recent studies where we can maintain the robus…
Unbiased Risk Estimators Can Mislead: A Case Study of Learning with Complementary Labels
Yu-Ting Chou, Gang Niu, Hsuan-Tien Lin +1
In weakly supervised learning, unbiased risk estimator(URE) is a powerful tool for training classifiers when training and test data are drawn from different distributions. Neverthe…
Provably Consistent Partial-Label Learning
Lei Feng, Jiaqi Lv, Bo Han +5
Partial-label learning (PLL) is a multi-class classification problem, where each training example is associated with a set of candidate labels. Even though many practical PLL metho…
Part-dependent Label Noise: Towards Instance-dependent Label Noise
Xiaobo Xia, Tongliang Liu, Bo Han +6
Learning with the \textit{instance-dependent} label noise is challenging, because it is hard to model such real-world noise. Note that there are psychological and physiological evi…
Class2Simi: A Noise Reduction Perspective on Learning with Noisy Labels
Songhua Wu, Xiaobo Xia, Tongliang Liu +5
Learning with noisy labels has attracted a lot of attention in recent years, where the mainstream approaches are in pointwise manners. Meanwhile, pairwise manners have shown great…
Dual T: Reducing Estimation Error for Transition Matrix in Label-noise Learning
Yu Yao, Tongliang Liu, Bo Han +4
The transition matrix, denoting the transition relationship from clean labels to noisy labels, is essential to build statistically consistent classifiers in label-noise learning. E…
Rethinking Importance Weighting for Deep Learning under Distribution Shift
Tongtong Fang, Nan Lu, Gang Niu +1
Under distribution shift (DS) where the training data distribution differs from the test one, a powerful technique is importance weighting (IW) which handles DS in two separate ste…
Multi-Class Classification from Noisy-Similarity-Labeled Data
Songhua Wu, Xiaobo Xia, Tongliang Liu +5
A similarity label indicates whether two instances belong to the same class while a class label shows the class of the instance. Without class labels, a multi-class classifier coul…
Attacks Which Do Not Kill Training Make Adversarial Learning Stronger
Jingfeng Zhang, Xilie Xu, Bo Han +4
Adversarial training based on the minimax formulation is necessary for obtaining adversarial robustness of trained models. However, it is conservative or even pessimistic so that i…
Do We Need Zero Training Loss After Achieving Zero Training Error?
Takashi Ishida, Ikko Yamane, Tomoya Sakai +2
Overparameterized deep networks have the capacity to memorize training data with zero \emph{training error}. Even after memorization, the \emph{training loss} continues to approach…
Progressive Identification of True Labels for Partial-Label Learning
Jiaqi Lv, Miao Xu, Lei Feng +3
Partial-label learning (PLL) is a typical weakly supervised learning problem, where each training instance is equipped with a set of candidate labels among which only one is the tr…
Rethinking Class-Prior Estimation for Positive-Unlabeled Learning
Yu Yao, Tongliang Liu, Bo Han +4
Given only positive (P) and unlabeled (U) data, PU learning can train a binary classifier without any negative data. It has two building blocks: PU class-prior estimation (CPE) and…
Confidence Scores Make Instance-dependent Label-noise Learning Possible
Antonin Berthon, Bo Han, Gang Niu +2
In learning with noisy labels, for every instance, its label can randomly walk to other classes following a transition distribution which is named a noise model. Well-studied noise…