A unifying review of deep and shallow anomaly detection
Deep learning approaches to anomaly detection (AD) have recently improved the state of
the art in detection performance on complex data sets, such as large collections of images or …
the art in detection performance on complex data sets, such as large collections of images or …
Partial label learning: Taxonomy, analysis and outlook
Partial label learning (PLL) is an emerging framework in weakly supervised machine
learning with broad application prospects. It handles the case in which each training …
learning with broad application prospects. It handles the case in which each training …
Debiased contrastive learning
A prominent technique for self-supervised representation learning has been to contrast
semantically similar and dissimilar pairs of samples. Without access to labels, dissimilar …
semantically similar and dissimilar pairs of samples. Without access to labels, dissimilar …
Combating noisy labels by agreement: A joint training method with co-regularization
Deep Learning with noisy labels is a practically challenging problem in weakly-supervised
learning. The state-of-the-art approaches" Decoupling" and" Co-teaching+" claim that the" …
learning. The state-of-the-art approaches" Decoupling" and" Co-teaching+" claim that the" …
Learning from positive and unlabeled data: A survey
Learning from positive and unlabeled data or PU learning is the setting where a learner only
has access to positive examples and unlabeled data. The assumption is that the unlabeled …
has access to positive examples and unlabeled data. The assumption is that the unlabeled …
Robust loss functions under label noise for deep neural networks
In many applications of classifier learning, training data suffers from label noise. Deep
networks are learned using huge training data where the problem of noisy labels is …
networks are learned using huge training data where the problem of noisy labels is …
Positive-unlabeled learning with non-negative risk estimator
From only positive (P) and unlabeled (U) data, a binary classifier could be trained with PU
learning, in which the state of the art is unbiased PU learning. However, if its model is very …
learning, in which the state of the art is unbiased PU learning. However, if its model is very …
Provably consistent partial-label learning
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 …
example is associated with a set of candidate labels. Even though many practical PLL …
Convex formulation for learning from positive and unlabeled data
M Du Plessis, G Niu… - … conference on machine …, 2015 - proceedings.mlr.press
We discuss binary classification from only from positive and unlabeled data (PU
classification), which is conceivable in various real-world machine learning problems. Since …
classification), which is conceivable in various real-world machine learning problems. Since …
Domain adaptation under open set label shift
S Garg, S Balakrishnan… - Advances in Neural …, 2022 - proceedings.neurips.cc
We introduce the problem of domain adaptation under Open Set Label Shift (OSLS), where
the label distribution can change arbitrarily and a new class may arrive during deployment …
the label distribution can change arbitrarily and a new class may arrive during deployment …