The sample selection approach is very popular in learning with noisy lab...
Training a classifier exploiting a huge amount of supervised data is
exp...
Learning from crowds describes that the annotations of training data are...
Robust generalization aims to tackle the most challenging data distribut...
Label noise poses a serious threat to deep neural networks (DNNs). Emplo...
Human motion prediction is a classical problem in computer vision and
co...
Machine learning models are vulnerable to Out-Of-Distribution (OOD) exam...
Pluralistic image completion focuses on generating both visually realist...
Deep networks have strong capacities of embedding data into latent
repre...
A more realistic object detection paradigm, Open-World Object Detection,...
Estimating the kernel mean in a reproducing kernel Hilbert space is a
cr...
The problem of open-set noisy labels denotes that part of training data ...
In learning with noisy labels, the sample selection approach is very pop...
The label noise transition matrix T, reflecting the probabilities that t...
Learning with the instance-dependent label noise is challenging,
because...
Label noise is ubiquitous in the era of big data. Deep learning algorith...
A similarity label indicates whether two instances belong to the same cl...
In label-noise learning, noise transition matrix, denoting the
probabili...